Search results for: learning image compression

Authors: Toktam Khatibi

Abstract:

Self-supervised learning (SSL) includes machine learning models that are trained on one aspect and/or one part of the input to learn other aspects and/or part of it. SSL models are divided into two different categories, including pre-text task-based models and contrastive learning ones. Pre-text tasks are some auxiliary tasks learning pseudo-labels, and the trained models are further fine-tuned for downstream tasks. However, one important disadvantage of SSL using pre-text task solving is defining an appropriate pre-text task for each image dataset with a variety of image modalities. Therefore, it is required to design an appropriate pretext task automatically for each dataset and each downstream task. To the best of our knowledge, the automatic designing of pretext tasks for image analysis has not been considered yet. In this paper, we present a framework based on In-context learning that describes each task based on its input and output data using a pre-trained image transformer. Our proposed method combines the input image and its learned description for optimizing the pre-text task design and its hyper-parameters using Meta-learning models. The representations learned from the pre-text tasks are fine-tuned for solving the downstream tasks. We demonstrate that our proposed framework outperforms the compared ones on unseen tasks and image modalities in addition to its superior performance for previously known tasks and datasets.

Keywords: in-context learning (ICL), meta learning, self-supervised learning (SSL), vision-language domain, transformers

Procedia PDF Downloads 48

Authors: Shaik Jilani Basha, Inavolu Avinash, Alla Venu Sai Reddy, Bitragunta Taraka Ramu

Abstract:

We can use the neural style transfer technique to build a picture with the same "content" as the beginning image but the "style" of the picture we've chosen. Neural style transfer is a technique for merging the style of one image into another while retaining its original information. The only change is how the image is formatted to give it an additional artistic sense. The content image depicts the plan or drawing, as well as the colors of the drawing or paintings used to portray the style. It is a computer vision programme that learns and processes images through deep convolutional neural networks. To implement software, we used to train deep learning models with the train data, and whenever a user takes an image and a styled image, the output will be as the style gets transferred to the original image, and it will be shown as the output.

Keywords: neural networks, computer vision, deep learning, convolutional neural networks

Procedia PDF Downloads 56

Authors: B. Ramesh Naik, T. Venugopal

Abstract:

This paper presents a novel approach which improves the high-level semantics of images based on machine learning approach. The contemporary approaches for image retrieval and object recognition includes Fourier transforms, Wavelets, SIFT and HoG. Though these descriptors helpful in a wide range of applications, they exploit zero order statistics, and this lacks high descriptiveness of image features. These descriptors usually take benefit of primitive visual features such as shape, color, texture and spatial locations to describe images. These features do not adequate to describe high-level semantics of the images. This leads to a gap in semantic content caused to unacceptable performance in image retrieval system. A novel method has been proposed referred as discriminative learning which is derived from machine learning approach that efficiently discriminates image features. The analysis and results of proposed approach were validated thoroughly on WANG and Caltech-101 Databases. The results proved that this approach is very competitive in content-based image retrieval.

Keywords: CBIR, discriminative learning, region weight learning, scale invariant feature transforms

Procedia PDF Downloads 148

Authors: Navdeep Goel, Salvador Gabarda

Abstract:

Digital images are widely used in computer applications. To store or transmit the uncompressed images requires considerable storage capacity and transmission bandwidth. Image compression is a means to perform transmission or storage of visual data in the most economical way. This paper explains about how images can be encoded to be transmitted in a multiplexing time-frequency domain channel. Multiplexing involves packing signals together whose representations are compact in the working domain. In order to optimize transmission resources each 4x4 pixel block of the image is transformed by a suitable polynomial approximation, into a minimal number of coefficients. Less than 4*4 coefficients in one block spares a significant amount of transmitted information, but some information is lost. Different approximations for image transformation have been evaluated as polynomial representation (Vandermonde matrix), least squares + gradient descent, 1-D Chebyshev polynomials, 2-D Chebyshev polynomials or singular value decomposition (SVD). Results have been compared in terms of nominal compression rate (NCR), compression ratio (CR) and peak signal-to-noise ratio (PSNR) in order to minimize the error function defined as the difference between the original pixel gray levels and the approximated polynomial output. Polynomial coefficients have been later encoded and handled for generating chirps in a target rate of about two chirps per 4*4 pixel block and then submitted to a transmission multiplexing operation in the time-frequency domain.

Keywords: chirp signals, image multiplexing, image transformation, linear canonical transform, polynomial approximation

Procedia PDF Downloads 393

Authors: Bhuyain Mobarok Hossain

Abstract:

Image classification and localization research is currently an important strategy in the field of computer vision. The evolution and advancement of deep learning and convolutional neural networks (CNN) have greatly improved the capabilities of object detection and image-based classification. Target detection is important to research in the field of computer vision, especially in video surveillance systems. To solve this problem, we will be applying a convolutional neural network of multiple scales at multiple locations in the image in one sliding window. Most translation networks move away from the bounding box around the area of interest. In contrast to this architecture, we consider the problem to be a classification problem where each pixel of the image is a separate section. Image classification is the method of predicting an individual category or specifying by a shoal of data points. Image classification is a part of the classification problem, including any labels throughout the image. The image can be classified as a day or night shot. Or, likewise, images of cars and motorbikes will be automatically placed in their collection. The deep learning of image classification generally includes convolutional layers; the invention of it is referred to as a convolutional neural network (CNN).

Keywords: image classification, object detection, localization, particle filter

Procedia PDF Downloads 271

Authors: Pawan Kumar Mishra, Ganesh Singh Bisht

Abstract:

Super-resolution is the technique that is being used in computer vision to construct high-resolution images from a single low-resolution image. It is used to increase the frequency component, recover the lost details and removing the down sampling and noises that caused by camera during image acquisition process. High-resolution images or videos are desired part of all image processing tasks and its analysis in most of digital imaging application. The target behind super-resolution is to combine non-repetition information inside single or multiple low-resolution frames to generate a high-resolution image. Many methods have been proposed where multiple images are used as low-resolution images of same scene with different variation in transformation. This is called multi-image super resolution. And another family of methods is single image super-resolution that tries to learn redundancy that presents in image and reconstruction the lost information from a single low-resolution image. Use of deep learning is one of state of art method at present for solving reconstruction high-resolution image. In this research, we proposed Deep Denoising Super Resolution (DDSR) that is a deep neural network for effectively reconstruct the high-resolution image from low-resolution image.

Keywords: resolution, deep-learning, neural network, de-blurring

Procedia PDF Downloads 486

Authors: Guofan Shao, Lina Tang, Hao Zhang

Abstract:

The values of image classification accuracy are affected by class size distributions and classification schemes, making it difficult to compare the performance of classification algorithms across different remote sensing data sources and classification systems. Based on the term efficacy from medicine and pharmacology, we have developed the metrics of image classification efficacy at the map and class levels. The novelty of this approach is that a baseline classification is involved in computing image classification efficacies so that the effects of class statistics are reduced. Furthermore, the image classification efficacies are interpretable and comparable, and thus, strengthen the assessment of image data classification methods. We use real-world and hypothetical examples to explain the use of image classification efficacies. The metrics of image classification efficacy meet the critical need to rectify the strategy for the assessment of image classification performance as image classification methods are becoming more diversified.

Keywords: accuracy assessment, efficacy, image classification, machine learning, uncertainty

Procedia PDF Downloads 179

Authors: Yanwen Li, Shuguo Xie

Abstract:

In electromagnetic imaging, because of the diffraction limited system, the pixel values could change slowly near the edge of the image targets and they also change with the location in the same target. Using traditional digital image segmentation methods to segment electromagnetic gradient images could result in lots of errors because of this change in pixel values. To address this issue, this paper proposes a novel image segmentation and extraction algorithm based on Mean-Shift and dictionary learning. Firstly, the preliminary segmentation results from adaptive bandwidth Mean-Shift algorithm are expanded, merged and extracted. Then the overlap rate of the extracted image block is detected before determining a segmentation region with a single complete target. Last, the gradient edge of the extracted targets is recovered and reconstructed by using a dictionary-learning algorithm, while the final segmentation results are obtained which are very close to the gradient target in the original image. Both the experimental results and the simulated results show that the segmentation results are very accurate. The Dice coefficients are improved by 70% to 80% compared with the Mean-Shift only method.

Keywords: gradient image, segmentation and extract, mean-shift algorithm, dictionary iearning

Procedia PDF Downloads 240

Authors: Chaitanya Chawla, Divya Panwar, Gurneesh Singh Anand, M. P. S Bhatia

Abstract:

This paper presents a deep-learning mechanism for classifying computer generated images and photographic images. The proposed method accounts for a convolutional layer capable of automatically learning correlation between neighbouring pixels. In the current form, Convolutional Neural Network (CNN) will learn features based on an image's content instead of the structural features of the image. The layer is particularly designed to subdue an image's content and robustly learn the sensor pattern noise features (usually inherited from image processing in a camera) as well as the statistical properties of images. The paper was assessed on latest natural and computer generated images, and it was concluded that it performs better than the current state of the art methods.

Keywords: image forensics, computer graphics, classification, deep learning, convolutional neural networks

Procedia PDF Downloads 306

Authors: D. Suman, B. Nikitha, J. Sarvani, V. Archana

Abstract:

Histological slides provide clinical diagnostic information about the subjects from the ancient times. Even with the advent of high resolution imaging cameras the image tend to have some background noise which makes the analysis complex. A study of the histological slides is done by using a nonlinear transfer function based image enhancement method. The method processes the raw, color images acquired from the biological microscope, which, in general, is associated with background noise. The images usually appearing blurred does not convey the intended information. In this regard, an enhancement method is proposed and implemented on 50 histological slides of human tissue by using nonlinear transfer function method. The histological image is converted into HSV color image. The luminance value of the image is enhanced (V component) because change in the H and S components could change the color balance between HSV components. The HSV image is divided into smaller blocks for carrying out the dynamic range compression by using a linear transformation function. Each pixel in the block is enhanced based on the contrast of the center pixel and its neighborhood. After the processing the V component, the HSV image is transformed into a colour image. The study has shown improvement of the characteristics of the image so that the significant details of the histological images were improved.

Keywords: HSV space, histology, enhancement, image

Procedia PDF Downloads 307

Authors: Michael Zimba

Abstract:

A duplicated image region may be subjected to a number of attacks such as noise addition, compression, reflection, rotation, and scaling with the intention of either merely mating it to its targeted neighborhood or preventing its detection. In this paper, we present an effective and robust method of detecting duplicated regions inclusive of those affected by the various attacks. In order to reduce the dimension of the image, the proposed algorithm firstly performs discrete wavelet transform, DWT, of a suspicious image. However, unlike most existing copy move image forgery (CMIF) detection algorithms operating in the DWT domain which extract only the low frequency sub-band of the DWT of the suspicious image thereby leaving valuable information in the other three sub-bands, the proposed algorithm simultaneously extracts features from all the four sub-bands. The extracted features are not only more accurate representation of image regions but also robust to additive noise, JPEG compression, and affine transformation. Furthermore, principal component analysis-eigenvalue decomposition, PCA-EVD, is applied to reduce the dimension of the features. The extracted features are then sorted using the more computationally efficient Radix Sort algorithm. Finally, same affine transformation selection, SATS, a duplication verification method, is applied to detect duplicated regions. The proposed algorithm is not only fast but also more robust to attacks compared to the related CMIF detection algorithms. The experimental results show high detection rates.

Keywords: affine transformation, discrete wavelet transform, radix sort, SATS

Procedia PDF Downloads 202

Authors: Bandar Alahmadi, Lethia Jackson

Abstract:

Machine Learning model is used today in many real-life applications. The safety and security of such model is important, so the results of the model are as accurate as possible. One challenge of machine learning model security is the adversarial examples attack. Adversarial examples are designed by the attacker to cause the machine learning model to misclassify the input. We propose a method to generate adversarial examples to attack image classifiers. We are modifying the successfully classified images, so a classifier misclassifies them after the modification. In our method, we do not update the whole image, but instead we detect the important region, modify it, place it back to the original image, and then run it through a classifier. The algorithm modifies the detected region using two methods. First, it will add abstract image matrix on back of the detected image matrix. Then, it will perform a rotation attack to rotate the detected region around its axes, and embed the trace of image in image background. Finally, the attacked region is placed in its original position, from where it was removed, and a smoothing filter is applied to smooth the background with foreground. We test our method in cascade classifier, and the algorithm is efficient, the classifier confident has dropped to almost zero. We also try it in CNN (Convolutional neural network) with higher setting and the algorithm was successfully worked.

Keywords: adversarial examples, attack, computer vision, image processing

Procedia PDF Downloads 312

Authors: Michael Zimba

Abstract:

A novel set of features for copy-move image forgery, CMIF, detection method is proposed. The proposed set presents a new approach which relies on electrostatic field theory, EFT. Solely for the purpose of reducing the dimension of a suspicious image, firstly performs discrete wavelet transform, DWT, of the suspicious image and extracts only the approximation subband. The extracted subband is then bijectively mapped onto a virtual electrostatic field where concepts of EFT are utilised to extract robust features. The extracted features are shown to be invariant to additive noise, JPEG compression, and affine transformation. The proposed features can also be used in general object matching.

Keywords: virtual electrostatic field, features, affine transformation, copy-move image forgery

Procedia PDF Downloads 520

Authors: Khalak Bin Khair, Saqib Jahir, Mohammed Ibrahim, Fahad Bin, Debajyoti Karmaker

Abstract:

Object detection is a computer technology that deals with searching through digital images and videos for occurrences of semantic elements of a particular class. It is associated with image processing and computer vision. On top of object detection, we detect camouflage objects within an image using Deep Learning techniques. Deep learning may be a subset of machine learning that's essentially a three-layer neural network Over 6500 images that possess camouflage properties are gathered from various internet sources and divided into 4 categories to compare the result. Those images are labeled and then trained and tested using vgg16 architecture on the jupyter notebook using the TensorFlow platform. The architecture is further customized using Transfer Learning. Methods for transferring information from one or more of these source tasks to increase learning in a related target task are created through transfer learning. The purpose of this transfer of learning methodologies is to aid in the evolution of machine learning to the point where it is as efficient as human learning.

Keywords: deep learning, transfer learning, TensorFlow, camouflage, object detection, architecture, accuracy, model, VGG16

Procedia PDF Downloads 105

Authors: Mohan Bilikallahalli Sannathimmappa, Vinod Nambiar, Rajeev Aravindakshan

Abstract:

Background: Image-based teaching-learning module is innovative student-centered andragogy. The objective of our study was to explore medical students’ perception of effectiveness of image-based learning strategy in promoting their lifelong learning skills and evaluate its impact on improving students’ exam grades. Methods: A prospective single-cohort study was conducted on undergraduate medical students of the academic year 2021-22. The image-based teaching-learning module was assessed through pretest, posttest, and exam grades. Students’ feedback was collected through a predesigned questionnaire on a 3-point Likert Scale. The reliability of the questionnaire was assessed using Cronbach’s alpha coefficient test. In-Course Exam-4 results were compared with In-Course Exams 1, 2, and 3. Correlation coefficients were worked out wherever relevant to find the impact of the exercise on grades. Data were collected, entered into Microsoft Excel, and statistically analyzed using SPSS version 22. Results: In total, 127 students were included in the study. The posttest scores of the students were significantly high (24.75±) as compared to pretest scores (8.25±). Students’ opinion towards the effectiveness of image-based learning in promoting their lifelong learning skills was overwhelmingly positive (Cronbach’s alpha for all items was 0.756). More than 80% of the students indicated image-based learning was interesting, encouraged peer discussion, and helped them to identify, explore, and revise key information and knowledge improvement. Nearly 70% expressed image-based learning enhanced their critical thinking and problem-solving skills. Nine out of ten students recommended image-based learning module for future topics. Conclusion: Overall, Image-based learning was found to be effective in achieving undergraduate medical students learning outcomes. The results of the study are in favor of the implementation of Image-based learning in Microbiology courses. However, multicentric studies are required to authenticate our study findings.

Keywords: active learning, knowledge, medical education, microbes, problem solving

Procedia PDF Downloads 52

Authors: Chhabi Nigam, S. Ramakrishnan

Abstract:

This paper brings out the analysis of the airborne Synthetic Aperture Radar (SAR) data to study the impact of Doppler centroid on Image quality and geocoding accuracy from the perspective of Stripmap mode of data acquisition. Although in Stripmap mode of data acquisition radar beam points at 90 degrees broad side (side looking), shift in the Doppler centroid is invariable due to platform motion. In-accurate estimation of Doppler centroid leads to poor image quality and image miss-registration. The effect of Doppler centroid is analyzed in this paper using multiple sets of data collected from airborne platform. Occurrences of ghost (ambiguous) targets and their power levels have been analyzed that impacts appropriate choice of PRF. Effect of aircraft attitudes (roll, pitch and yaw) on the Doppler centroid is also analyzed with the collected data sets. Various stages of the RDA (Range Doppler Algorithm) algorithm used for image formation in Stripmap mode, range compression, Doppler centroid estimation, azimuth compression, range cell migration correction are analyzed to find the performance limits and the dependence of the imaging geometry on the final image. The ability of Doppler centroid estimation to enhance the imaging accuracy for registration are also illustrated in this paper. The paper also tries to bring out the processing of low squint SAR data, the challenges and the performance limits imposed by the imaging geometry and the platform dynamics on the final image quality metrics. Finally, the effect on various terrain types, including land, water and bright scatters is also presented.

Keywords: ambiguous target, Doppler Centroid, image registration, Airborne SAR

Procedia PDF Downloads 188

Authors: Muhammad Maqsood, Yasir Nawab, Syed Talha Ali Hamdani

Abstract:

Stretchable fabrics have diverse applications ranging from casual apparel to performance sportswear and compression therapy. Compression therapy is the universally accepted treatment for the management of hypertrophic scarring after severe burns. Mostly stretchable knitted fabrics are used in compression therapy but in the recent past, some studies have also been found on bi-stretch woven fabrics being used as compression garments as they also have been found quite effective in the treatment of oedema. Therefore, the objective of the present study is to compare the compression properties of stretchable knitted and bi-stretch woven fabrics for compression garments. For this purpose four woven structures and four knitted structures were produced having the same areal density and their compression, comfort and mechanical properties were compared before and after 5, 10 and 15 washes. Four knitted structures used were single jersey, single locaste, plain pique and the honeycomb, whereas four woven structures produced were 1/1 plain, 2/1 twill, 3/1 twill and 4/1 twill. The compression properties of the produced samples were tested by using kikuhime pressure sensor and it was found that bi-stretch woven fabrics possessed better compression properties before and after washes and retain their durability after repeated use, whereas knitted stretchable fabrics lost their compression ability after repeated use and the required sub garment pressure of the knitted structures after 15 washes was almost half to that of woven bi-stretch fabrics.

Keywords: compression garments, knitted structures, medical textiles, woven bi-stretch

Procedia PDF Downloads 377

Authors: Mirjana Ruppel, Rajendra Persad, Amit Bahl, Sanja Dogramadzi, Chris Melhuish, Lyndon Smith

Abstract:

Multimodal image registration is a profoundly complex task which is why deep learning has been used widely to address it in recent years. However, two main challenges remain: Firstly, the lack of ground truth data calls for an unsupervised learning approach, which leads to the second challenge of defining a feasible loss function that can compare two images of different modalities to judge their level of alignment. To avoid this issue altogether we implement a generative adversarial network consisting of two registration networks GAB, GBA and two discrimination networks DA, DB connected by spatial transformation layers. GAB learns to generate a deformation field which registers an image of the modality B to an image of the modality A. To do that, it uses the feedback of the discriminator DB which is learning to judge the quality of alignment of the registered image B. GBA and DA learn a mapping from modality A to modality B. Additionally, a cycle-consistency loss is implemented. For this, both registration networks are employed twice, therefore resulting in images ˆA, ˆB which were registered to ˜B, ˜A which were registered to the initial image pair A, B. Thus the resulting and initial images of the same modality can be easily compared. A dataset of liver CT and MRI was used to evaluate the quality of our approach and to compare it against learning and non-learning based registration algorithms. Our approach leads to dice scores of up to 0.80 ± 0.01 and is therefore comparable to and slightly more successful than algorithms like SimpleElastix and VoxelMorph.

Keywords: cycle consistency, deformable multimodal image registration, deep learning, GAN

Procedia PDF Downloads 101

Authors: Vaishnavi Shivde, Shrishti Sinha, Trapti Mishra

Abstract:

Traffic light detection from a moving vehicle is an important technology both for driver safety assistance functions as well as for autonomous driving in the city. This paper proposed a deep-learning-based traffic light recognition method that consists of a pixel-wise image segmentation technique and a fully convolutional network i.e., UNET architecture. This paper has used a method for detecting the position and recognizing the state of the traffic lights in video sequences is presented and evaluated using Traffic Light Dataset which contains masked traffic light image data. The first stage is the detection, which is accomplished through image processing (image segmentation) techniques such as image cropping, color transformation, segmentation of possible traffic lights. The second stage is the recognition, which means identifying the color of the traffic light or knowing the state of traffic light which is achieved by using a Convolutional Neural Network (UNET architecture).

Keywords: traffic light detection, image segmentation, machine learning, classification, convolutional neural networks

Procedia PDF Downloads 139

Authors: P. Karthick, K. Mahesh

Abstract:

Video has become an increasingly significant component of our digital everyday contact. With the advancement of greater contents and shows of the resolution, its significant volume poses serious obstacles to the objective of receiving, distributing, compressing, and revealing video content of high quality. In this paper, we propose the primary beginning to complete a deep video compression model that jointly upgrades all video compression components. The video compression method involves splitting the video into frames, comparing the images using convolutional neural networks (CNN) to remove duplicates, repeating the single image instead of the duplicate images by recognizing and detecting minute changes using generative adversarial network (GAN) and recorded with long short-term memory (LSTM). Instead of the complete image, the small changes generated using GAN are substituted, which helps in frame level compression. Pixel wise comparison is performed using K-nearest neighbours (KNN) over the frame, clustered with K-means, and singular value decomposition (SVD) is applied for each and every frame in the video for all three color channels [Red, Green, Blue] to decrease the dimension of the utility matrix [R, G, B] by extracting its latent factors. Video frames are packed with parameters with the aid of a codec and converted to video format, and the results are compared with the original video. Repeated experiments on several videos with different sizes, duration, frames per second (FPS), and quality results demonstrate a significant resampling rate. On average, the result produced had approximately a 10% deviation in quality and more than 50% in size when compared with the original video.

Keywords: video compression, K-means clustering, convolutional neural network, generative adversarial network, singular value decomposition, pixel visualization, stochastic gradient descent, frame per second extraction, RGB channel extraction, self-detection and deciding system

Procedia PDF Downloads 162

Authors: Ahmad FAROOQ, Xinfeng Zhang, Fahad Sabah, Raheem Sarwar

Abstract:

In Traditional Chinese Medicine, tongue diagnosis is a vital inspection tool (TCM). In this study, we explore the potential of machine learning in tongue diagnosis. It begins with the cataloguing of the various classifications and characteristics of the human tongue. We infer 24 kinds of tongues from the material and coating of the tongue, and we identify 21 attributes of the tongue. The next step is to apply machine learning methods to the tongue dataset. We use the Weka machine learning platform to conduct the experiment for performance analysis. The 457 instances of the tongue dataset are used to test the performance of five different machine learning methods, including SVM, Random Forests, Decision Trees, and Naive Bayes. Based on accuracy and Area under the ROC Curve, the Support Vector Machine algorithm was shown to be the most effective for tongue diagnosis (AUC).

Keywords: medical imaging, image retrieval, machine learning, tongue

Procedia PDF Downloads 42

Authors: Cristina Maria Ribeiro Martins Pereira Caridade, Ana Rita Ferreira Morais

Abstract:

The use of computational tools has become essential in the context of interactive learning, especially in engineering education. In the medical industry, teaching medical image processing techniques is a crucial part of training biomedical engineers, as it has integrated applications with healthcare facilities and hospitals. The aim of this article is to present a teaching-learning simulation tool developed in MATLAB using a graphical user interface for medical image fusion that explores different image fusion methodologies and processes in combination with image pre-processing techniques. The application uses different algorithms and medical fusion techniques in real time, allowing you to view original images and fusion images, compare processed and original images, adjust parameters, and save images. The tool proposed in an innovative teaching and learning environment consists of a dynamic and motivating teaching simulation for biomedical engineering students to acquire knowledge about medical image fusion techniques and necessary skills for the training of biomedical engineers. In conclusion, the developed simulation tool provides real-time visualization of the original and fusion images and the possibility to test, evaluate and progress the student’s knowledge about the fusion of medical images. It also facilitates the exploration of medical imaging applications, specifically image fusion, which is critical in the medical industry. Teachers and students can make adjustments and/or create new functions, making the simulation environment adaptable to new techniques and methodologies.

Keywords: image fusion, image processing, teaching-learning simulation tool, biomedical engineering education

Procedia PDF Downloads 89

Authors: Sangeeta Palekar, Neeraj Rangwani, Akash Poddar, Jayu Kalambe

Abstract:

The bio-medical analysis is an indispensable procedure for identifying health-related diseases like diabetes. Monitoring the glucose level in our body regularly helps us identify hyperglycemia and hypoglycemia, which can cause severe medical problems like nerve damage or kidney diseases. This paper presents a method for predicting the glucose concentration in blood samples using image processing and machine learning algorithms. The glucose solution is prepared by the glucose oxidase (GOD) and peroxidase (POD) method. An experimental database is generated based on the colorimetric technique. The image of the glucose solution is captured by the raspberry pi camera and analyzed using image processing by extracting the RGB, HSV, LUX color space values. Regression algorithms like multiple linear regression, decision tree, RandomForest, and XGBoost were used to predict the unknown glucose concentration. The multiple linear regression algorithm predicts the results with 97% accuracy. The image processing and machine learning-based approach reduce the hardware complexities of existing platforms.

Keywords: artificial intelligence glucose detection, glucose oxidase, peroxidase, image processing, machine learning

Procedia PDF Downloads 171

Authors: T. R. Sharika, Ashwini Kumar, Kamal Bijlani

Abstract:

Encryption is the process of converting crucial information’s unreadable to unauthorized persons. Image security is an important type of encryption that secures all type of images from cryptanalysis. A stream cipher is a fast symmetric key algorithm which is used to convert plaintext to cipher text. In this paper we are proposing an image encryption algorithm with Discrete Cosine Transform and Stream Ciphers that can improve compression of images and enhanced security. The paper also explains the use of a shuffling algorithm for enhancing securing.

Keywords: decryption, DCT, encryption, RC4 cipher, stream cipher

Procedia PDF Downloads 338

Authors: Nguyen J. M., Lucas G., Brunner M., Ruan S., Antonioli D.

Abstract:

Deep learning based on convolutional neural networks (CNN) is a very powerful technique for classifying information from an image. We propose a new method, DeepNic, to transform each variable of a tabular dataset into an image where each pixel represents a set of conditions that allow the variable to make an error-free prediction. The contrast of each pixel is proportional to its prediction performance and the color of each pixel corresponds to a sub-family of NICs. NICs are probabilities that depend on the number of inputs to each neuron and the range of coefficients of the inputs. Each variable can therefore be expressed as a function of a matrix of 2 vectors corresponding to an image whose pixels express predictive capabilities. Our objective is to transform each variable of tabular data into images into an image that can be analysed by CNNs, unlike other methods which use all the variables to construct an image. We analyse the NIC information of each variable and express it as a function of the number of neurons and the range of coefficients used. The predictive value and the category of the NIC are expressed by the contrast and the color of the pixel. We have developed a pipeline to implement this technology and have successfully applied it to genomic expressions on an Affymetrix chip.

Keywords: tabular data, deep learning, perfect trees, NICS

Procedia PDF Downloads 59

Authors: Revoti Prasad Bora, Nikita Katyal, Saurabh Yadav

Abstract:

Pre-processing plays an important role in various image processing applications. Most of the time due to the similar nature of images, a particular pre-processing or a set of pre-processing steps are sufficient to produce the desired results. However, in the education domain, there is a wide variety of images in various aspects like images with line-based diagrams, chemical formulas, mathematical equations, etc. Hence a single pre-processing or a set of pre-processing steps may not yield good results. Therefore, a Deep Learning based approach for dynamically selecting a relevant pre-processing technique for each image is proposed. The proposed method works as a classifier to detect hidden patterns in the images and predicts the relevant pre-processing technique needed for the image. This approach experimented for an image similarity matching problem but it can be adapted to other use cases too. Experimental results showed significant improvement in average similarity ranking with the proposed method as opposed to static pre-processing techniques.

Keywords: deep-learning, classification, pre-processing, computer vision, image processing, educational data mining

Procedia PDF Downloads 120

Authors: Lizhou Chen, Abdelhamid Belgaid, Assem Elsayed, Xiaoming Yang

Abstract:

Compression index is essential in foundation settlement calculation. The traditional method for determining compression index is consolidation test which is expensive and time consuming. Many researchers have used regression methods to develop empirical equations for predicting compression index from soil properties. Based on a large number of compression index data collected from consolidation tests, the accuracy of some popularly empirical equations were assessed. It was found that primary compression index is significantly overestimated in some equations while it is underestimated in others. The sensitivity analyses of soil parameters including water content, liquid limit and void ratio were performed. The results indicate that the compression index obtained from void ratio is most accurate. The ANOVA (analysis of variance) demonstrates that the equations with multiple soil parameters cannot provide better predictions than the equations with single soil parameter. In other words, it is not necessary to develop the relationships between compression index and multiple soil parameters. Meanwhile, it was noted that secondary compression index is approximately 0.7-5.0% of primary compression index with an average of 2.0%. In the end, the proposed prediction equations using power regression technique were provided that can provide more accurate predictions than those from existing equations.

Keywords: compression index, clay, settlement, consolidation, secondary compression index, soil parameter

Procedia PDF Downloads 134

Authors: Prathiksha Kamath, Pratibha Jamkhandi, Prateek Ghanti, Priyanshu Gupta, M. Lakshmi Neelima

Abstract:

Combining Image Captioning and Visual Question Answering (VQA) tasks have emerged as a new and exciting research area. The image captioning task involves generating a textual description that summarizes the content of the image. VQA aims to answer a natural language question about the image. Both these tasks include computer vision and natural language processing (NLP) and require a deep understanding of the content of the image and semantic relationship within the image and the ability to generate a response in natural language. There has been remarkable growth in both these tasks with rapid advancement in deep learning. In this paper, we present a comprehensive review of recent progress in combining image captioning and visual question-answering (VQA) tasks. We first discuss both image captioning and VQA tasks individually and then the various ways in which both these tasks can be integrated. We also analyze the challenges associated with these tasks and ways to overcome them. We finally discuss the various datasets and evaluation metrics used in these tasks. This paper concludes with the need for generating captions based on the context and captions that are able to answer the most likely asked questions about the image so as to aid the VQA task. Overall, this review highlights the significant progress made in combining image captioning and VQA, as well as the ongoing challenges and opportunities for further research in this exciting and rapidly evolving field, which has the potential to improve the performance of real-world applications such as autonomous vehicles, robotics, and image search.

Keywords: image captioning, visual question answering, deep learning, natural language processing

Procedia PDF Downloads 51

Authors: Seyed Mehdi Seyed Alizadeh, Christoph Arns, Shane Latham

Abstract:

Geomechanical characterization of rocks in detail and its possible implications on flow properties is an important aspect of reservoir characterization workflow. In order to gain more understanding of the microstructure evolution of reservoir rocks under stress a series of axisymmetric triaxial tests were performed on two different analogue rock samples. In-situ compression tests were coupled with high resolution micro-Computed Tomography to elucidate the changes in the pore/grain network of the rocks under pressurized conditions. Two outcrop sandstones were chosen in the current study representing a various cementation status of well-consolidated and weakly-consolidated granular system respectively. High resolution images were acquired while the rocks deformed in a purpose-built compression cell. A detailed analysis of the 3D images in each series of step-wise compression tests (up to the failure point) was conducted which includes the registration of the deformed specimen images with the reference pristine dry rock image. Digital Image Correlation (DIC) technique based on the intensity of the registered 3D subsets and particle tracking are utilized to map the displacement fields in each sample. The results suggest the complex architecture of the localized shear zone in well-cemented Bentheimer sandstone whereas for the weakly-consolidated Castlegate sandstone no discernible shear band could be observed even after macroscopic failure. Post-mortem imaging a sister plug from the friable rock upon undergoing continuous compression reveals signs of a shear band pattern. This suggests that for friable sandstones at small scales loading mode may affect the pattern of deformation. Prior to mechanical failure, the continuum digital image correlation approach can reasonably capture the kinematics of deformation. As failure occurs, however, discrete image correlation (i.e. particle tracking) reveals superiority in both tracking the grains as well as quantifying their kinematics (in terms of translations/rotations) with respect to any stage of compaction. An attempt was made to quantify the displacement field in compression using continuum Digital Image Correlation which is based on the reference and secondary image intensity correlation. Such approach has only been previously applied to unconsolidated granular systems under pressure. We are applying this technique to sandstones with various degrees of consolidation. Such element of novelty will set the results of this study apart from previous attempts to characterize the deformation pattern in consolidated sands.

Keywords: deformation mechanism, displacement field, shear behavior, triaxial compression, X-ray micro-CT

Procedia PDF Downloads 159

Authors: Shayan Mohajer Hamidi

Abstract:

Federated learning has emerged as a promising approach for distributed model training while preserving data privacy. However, the challenges of communication overhead, limited network resources, and slow convergence hinder its widespread adoption. On the other hand, knowledge distillation has shown great potential in compressing large models into smaller ones without significant loss in performance. In this paper, we propose an innovative framework that combines federated learning and knowledge distillation to address these challenges and enhance the efficiency of distributed learning. Our approach, called Federated Knowledge Distillation (FKD), enables multiple clients in a federated learning setting to collaboratively distill knowledge from a teacher model. By leveraging the collaborative nature of federated learning, FKD aims to improve model compression while maintaining privacy. The proposed framework utilizes a coded teacher model that acts as a reference for distilling knowledge to the client models. To demonstrate the effectiveness of FKD, we conduct extensive experiments on various datasets and models. We compare FKD with baseline federated learning methods and standalone knowledge distillation techniques. The results show that FKD achieves superior model compression, faster convergence, and improved performance compared to traditional federated learning approaches. Furthermore, FKD effectively preserves privacy by ensuring that sensitive data remains on the client devices and only distilled knowledge is shared during the training process. In our experiments, we explore different knowledge transfer methods within the FKD framework, including Fine-Tuning (FT), FitNet, Correlation Congruence (CC), Similarity-Preserving (SP), and Relational Knowledge Distillation (RKD). We analyze the impact of these methods on model compression and convergence speed, shedding light on the trade-offs between size reduction and performance. Moreover, we address the challenges of communication efficiency and network resource utilization in federated learning by leveraging the knowledge distillation process. FKD reduces the amount of data transmitted across the network, minimizing communication overhead and improving resource utilization. This makes FKD particularly suitable for resource-constrained environments such as edge computing and IoT devices. The proposed FKD framework opens up new avenues for collaborative and privacy-preserving distributed learning. By combining the strengths of federated learning and knowledge distillation, it offers an efficient solution for model compression and convergence speed enhancement. Future research can explore further extensions and optimizations of FKD, as well as its applications in domains such as healthcare, finance, and smart cities, where privacy and distributed learning are of paramount importance.

Keywords: federated learning, knowledge distillation, knowledge transfer, deep learning

Procedia PDF Downloads 44