Learning Aided Digital Image Compression Technique for Medical Application

The explosive growths in data exchanges have necessitated the development of new methods of image compression including use of learning based techniques. The learning based systems aids proper compression and retrieval of the image segments. Learning systems like. Artificial Neural Networks (ANN) have established their efficiency and reliability in achieving image compression. In this work, two approaches to use ANNs in Feed Forward (FF) form and another based on Self Organizing Feature Map (SOFM) is proposed for digital image compression. The image to be compressed is first decomposed into smaller blocks and passed to FFANN and SOFM networks for generation of codebooks. The compressed images are reconstructed using a composite block formed by a FFANN and a Discrete Cosine Transform (DCT) based compression-decompression system. Mean Square Error (MSE), Compression ratio (CR) and Peak Signal-to-Noise Ratio (PSNR) are used to evaluate the performance of the system.

A Novel Fuzzy Logic Classifier for Classification and Quality Measurement of Apple Fruit

Fruit and vegetables market is getting highly selective and requiring their suppliers to distribute the fruits of high standards of quality and good appearance. So the growing need to supply quality fruits within a short period of time has given rise to development of Automated Grading of fresh market fruits. The objective of this chapter is to classify apples into three grades based on its attributes such as color, size and weight. Initially apple image database is created. Next each image is analyzed using image processing software where images are first preprocessed and useful features like color and size are extracted from the images. Fuzzy logic is used for classification. Color, size features are represented as a fuzzy variables which are used for classification. The apples of different classes are graded into three grades viz. Grade1, Grade2 and Grade3 on the basis of combination of parameters mentioned above.

Biometric Identification System Using Neuro and Fuzzy Computational Approaches

In all authentication systems, biometric samples are regarded to be the most reliable one. Biometric samples like fingerprint, retina etc. is unique. Most commonly available biometric system prefers these samples as reliable inputs. In a biometric authentication system, the design of decision support system is critical and it determines success or failure. Here, we propose such a system based on neuro and fuzzy system. Neuro systems formulated using Artificial Neural Network learn from numeric data while fuzzy based approaches can track finite variations in the environment. Thus NFS systems formed using ANN and fuzzy system demonstrate adaptive, numeric and qualitative processing based learning. These attributes have motivated the formulation of an adaptive neuro fuzzy inference system which is used as a DSS of a biometric authenticable system. The experimental results show that the system is reliable and can be considered to be a part of an actual design.

Improved Lymphocyte Image Segmentation Using Near Sets for ALL Detection

Light microscopic examination of peripheral blood smear is considered vital for diagnosis of various hematological disorders. The objective of this paper is to develop a fast, robust and simple framework for blood microscopic image segmentation which can assist in automated detection of hematological diseases i.e. acute lymphoblastic leukemia (ALL). A near set based clustering approach is followed for color based segmentation of lymphocyte blood image. Here, a novel distance measure using near sets has been introduced. This improved nearness distance measure has been used in a clustering framework for achieving accurate lymphocyte image segmentation. The nearness measure determines the degree to which two pixels resemble each other based on a defined probe function. It is essential as image segmentation is considered here as a colour based pixel clustering problem. Lymphocyte image segmentation algorithm developed here labels each pixel into nucleus, cytoplasm or background region based on the nearness measure.

Intelligence-Based Adaptive Digital Watermarking for Images in Wavelet Transform Domain

Advances in technologies facilitate the end users to carry out unauthorized manipulation and duplication of multimedia data with less effort. Because of these advancements, the two most commonly encountered problems are (1) copyright protection and (2) unauthorized manipulation of multimedia data. Thus a scheme is required to protect multimedia data from those two above said problems. Digital Watermarking is considered as one of the security mechanisms to protect copyrights of multimedia data. The literature review reveals that the calculation of scaling and embedding parameters are not completely automated. In order to automate the procedure of calculating scaling and embedding parameters the computational intelligence need to be incorporated in the watermarking algorithm. Moreover the quality of the watermarked images could also be preserved by combining computational intelligence concepts. Thus watermarking schemes utilizing computational intelligence concepts could be called as intelligence based watermarking schemes and it is presented in this chapter in detail.

Face Recognition in Unconstrained Environment

Research emphasizes in face recognition has shifted towards recognition of human from both still images and videos which are captured in unconstrained imaging environments and without user cooperation. Due to confounding factors of pose, illumination, image quality, and expression, as well as occlusion and low resolution, current face recognition systems deployed in forensic and security applications operate in a semi-automatic manner. This book chapter presents a comprehensive review of face recognition approaches in unconstrained environment. The objective of this book chapter is to address issues, challenges and recent advancement in face recognition algorithms which may help novel researchers to do innovative research in unconstrained environment. Finally, this chapter provides the stepping stone for future research to unveil how biometrics approaches can be deployed in unconstrained face recognition systems.

Total Variation Applications in Computer Vision

The objectives of this chapter are: (i) to introduce a concise overview of regularization; (ii) to define and to explain the role of a particular type of regularization called total variation norm (TV-norm) in computer vision tasks; (iii) to set up a brief discussion on the mathematical background of TV methods; and (iv) to establish a relationship between models and a few existing methods to solve problems cast as TV-norm. For the most part, image-processing algorithms blur the edges of the estimated images, however TV regularization preserves the edges with no prior information on the observed and the original images. The regularization scalar parameter ? controls the amount of regularization allowed and it is essential to obtain a high-quality regularized output. A wide-ranging review of several ways to put into practice TV regularization as well as its advantages and limitations are discussed.

Application of Charge System Search Algorithm for Data Clustering

This chapter presents a charged system search (CSS) optimization method for finding the optimal cluster centers for a given dataset. In CSS algorithm, while the Coulomb and Gauss laws from electrostatics are applied to initiate the local search, global search is performed using Newton second law of motion from mechanics. The efficiency and capability of the proposed algorithm is tested on seven datasets and compared with existing algorithms like K-Means, GA, PSO and ACO. From the experimental results, it is found that the proposed algorithm provides more accurate and effective results in comparison to other existing algorithms.

Impulse Noise Filtering

Digital images are often corrupted by various types of noises amongst which impulse noise is most prevalent. Impulse noise appears during transmission and/or acquisition of images. Intrusion of impulse noise degrades the quality of the image and causes the loss of fine image details. Reducing the effect of impulse noise from corrupted images is therefore considered as an essential task to be performed before letting the image for further processing. However, the process of noise reduction from an image should also take proper care towards the preservation of edges and fine details of an image. A number of efficient noise reduction algorithms have already been proposed in the literature over the last few decades which have nurtured this issue with utmost importance. Design and development of new two dimensional (2D) filters has grown sufficient interest amongst the researchers. This chapter attempts to throw enough light on the advancement in this field by illustratively describing existing state-of-the-art filtering techniques along with their capability of denoising impulse noises.

Image Data Mining Based on Wavelet Transform for Visualization of the Unique Characteristics of Image Data

Mining techniques can play an important role in image decomposition, segmentation, classification and retrieval systems. As image data become more complex and growing at a fast pace, searching valuable information and knowledge implicit become more challenging than ever before. In this chapter, authors proposed a WT based DM techniques to optimize and characterize the unique feature of image retrieval, which is fundamental to optimize informative mathematical representation of image objects. Many software, including data exploratory tools such as DM packages contain fast and efficient programs that perform WT. Wavelets have quickly gained popularity among scientists and engineers, both in theoretical research and in applications. The authors discussed in details and introduced a novel method for image database analysis in different scenarios that foster the wide access of image data.