Full Description
This book introduces readers to innovative bio-inspired computing techniques for image processing applications. It demonstrates how a significant drawback of image processing - not providing the simultaneous benefits of high accuracy and less complexity - can be overcome, proposing bio-inspired methodologies to help do so.
Besides computing techniques, the book also sheds light on the various application areas related to image processing, and weighs the pros and cons of specific methodologies. Even though several such methodologies are available, most of them do not provide the simultaneous benefits of high accuracy and less complexity, which explains their low usage in connection with practical imaging applications, such as the medical scenario. Lastly, the book illustrates the methodologies in detail, making it suitable for newcomers to the field and advanced researchers alike.
Contents
Artifical Bee Colony Algorithm for Classification of Semi-Urban LU/LC Features Using High Resolution Satellite Data.- Saliency Based Image Compression Using Walsh-Hadamard Transform (WHT).- Object trajectory prediction with scarce environment information.- A Two-fold Subspace Learning Based Feature Fusion Strategy for Classification of EMG and EMG spectrogram Images.- Automatic Detection of Brain Strokes in CT Images using Soft Computing Techniques.- A survey on Intelligence based biometric techniques for authentication applications.- Spatial and Spectral Quality Assessment of Fused Hyperspectral and Multispectral Data.- Deep Learning Techniques for Breast Cancer Detection using Medical Images Analysis.- A Tour towards the development of various Techniques for Paralysis Detection using Image Processing.- Chlorella - Algae Image Analysis using Artificial Neural Network and Deep Learning.- Review on Image Enhancement Techniques using Biologically Inspired Artificial Bee ColonyAlgorithms and its variants.- Certain Applications and Case Studies of Evolutionary Computing Techniques for Image Processing.- Histopathological Image Analysis for the Grade Identification of Tumor.- Super Resolution via Particle Swarm Optimization Variants.
