NON-INVASIVE NEONATAL GOLDEN HUE DETECTOR
Species Classification and Disease Identification Using Image Processing and Convolutional Neural Networks
A novel meta-heuristic jellyfish Optimize for Detection and Recognition of Text from complex images
Rice Leaf Disease Detection Using Convolutional Neural Network
Comparative Analysis of usage of Machine learning in Image Recognition
Identification of Volcano Hotspots by using Resilient Back Propagation (RBP) Algorithm Via Satellite Images
Data Hiding in Encrypted Compressed Videos for Privacy Information Protection
Improved Video Watermarking using Discrete Cosine Transform
Contrast Enhancement based Brain Tumour MRI Image Segmentation and Detection with Low Power Consumption
Denoising of Images by Wavelets and Contourlets using Bi-Shrink Filter
IP video traffic on the network continues to grow. To account for a future traffic of a million minutes of videos per second, it is important to minimize the traffic each video generates. This is a performance comparison of the HEVC, AV1, and xvc (in fast mode) video CODECs with the focus on minimizing network traffic for common use cases, such as video conferences and social media video streaming, these being used, where less than optimal videos are sent. The purpose is to identify which CODEC gives the best quality at the lowest bit rate. This is done by running a test bench with multiple videos of different qualities, encoding and decoding each video with each CODEC. The study shows that xvc (fast mode) and AV1 (double-pass) has similar quality performance on the dataset and has a noticeable improvement compared to HEVC (double-pass) when it comes to less optimal video quality. This research work was conducted in the context of the course II2202 Research Methodology and Scientific Writing at KTH Royal Institute of Technology, Sweden.
The traditional approaches to the classification of image regions suffer drawbacks in the face of imaging conditions (occlusion, illumination changes, rotation, viewpoint changes, and image blurring) and thus contribute to the poor performance of several vision based applications, such as object recognition, object tracking, image retrieval, pose estimation, camera calibration, 3D reconstruction, Structure from motion, stereo images, and image stitching. However, in this work, feature points extraction method by decomposition of image structure is employed in order to overcome these challenges. The decomposition of an image structure into feature set enhances the performance of many vision-based applications and system. The feature point extraction method which we refer to as Upright Feature from Accelerated Segment Test with Harris filter (UFAH) in this text, works by combining Feature from Accelerated Segment Test detector with Harris filter. The result obtained in the evaluation process shows that UFAH is robust and also invariant to imaging conditions (i.e rotation, illumination changes, and image blurring).
The aim of this paper is to present an image compression method using feedforward backpropagation neural networks. Medical imaging is an efficient source for better diagnosis of the disease and also helps in assessing the severity of the disease. But due to the increasing size of the medical images, transferring and storage of images require huge bandwidth and storage space. Therefore, it is essential to derive an effective compression algorithm, which have minimal loss, time complexity, and increased reduction in size. With the concept of Neural Network, data compression can be achieved by producing an internal data representation. The training algorithm and development architecture gives less distortion and considerable compression ratio and also keeps up the capability of hypothesizing and is becoming important. The performance metrics of three algorithms, Levenberg Marquardt algorithm, Resilient backpropagation algorithm, and Gradient Decent algorithm have been computed on Magnetic Resonance Imaging (MRI) images and it is observed that Levenberg Marquardt algorithm is more accurate when compared to the other two algorithms.
Blood cancer or leukemia detection using microscopic images is a challenging task considering the fact that variations in blood cell patterns are miniscule in nature and human detection may be prone to errors due to inherent deficiencies or anomalies in the dataset or due to human errors. Hence using automated classification has been considered using data pre-processing techniques such as Artificial Neural Networks and Fuzzy Logic. Recently, a new domain of research called neuro-fuzzy systems has garnered a lot of attention due to its efficacy. This paper introduces the challenges faced in the detection and classification of blood leukemia. Along with it, the paper focuses on the various significant contributions in the field by different researchers. This may pave the path for further improvement in accuracy of classification of leukemia.
The essential part of any ecosystem is plant. All the organisms get energy from plants directly or indirectly. It is important to identify the disease in plant parts like leaf, stem, and fruit. Leaf diseases are caused by virus, bacteria, etc. Normally, a farmer identifies the leaf disease by observing spots, color, and shape of the leaf, but sometimes they take help from the experts to detect diseased leaf or crops. The manual detection of disease is less accurate and complex. Image processing techniques help farmers for timely detection of the diseases. K-Nearest Neighbor (KNN), K-Means clustering, Support Vector Machine (SVM), Artificial Neural Network (ANN), and various segmentation algorithm and classifiers are used for detection and classification of leaf diseases. In this paper, various diseases that occur in parts of the plant and identification of leaf diseases were discussed.
