An Algorithmic Approach Based on CMS Edge Detection Technique for the Processing of Digital Images

Research in the field of digital image processing (DIP) has increased in the current scenario. Edge detection of digital images is considered as an important area of research in DIP. Detecting edges in different digital images accurately is a challenging work in DIP. Different methods have been introduced by different researchers to detect the edges of images. However, no method works well under all conditions. In this chapter, an edge detection method is proposed to detect the edges of gray scale and color images. This method focuses on the combination of Canny, mathematical morphological, and Sobel (CMS) edge detection operators. The output of the proposed method is produced using matrix laboratory (MATLAB) R2015b and compared with Sobel, Prewitt, Roberts, Laplacian of Gaussian (LoG), Canny, and mathematical morphological edge detection operators. The experimental results show that the proposed method works better as compared to other existing methods in detecting the edges of images.

Image Enhancement

This chapter describes a novel method to enhance degraded nighttime images by dehazing and color correction method. In the first part of this chapter, the authors focus on filtering process for low illumination images. Secondly, they propose an efficient dehazing model for removing haziness Thirdly, a color correction method proposed for color consistency approach. Removing nighttime haze technique is an important and necessary procedure to avoid ill-condition visibility of human eyes. Scattering and color distortion are two major problems of distortion in case of hazy image. To increase the visibility of the scene, the authors compute the preprocessing using WLS filter. Then the airlight component for the non-uniform illumination presents in nighttime scenes is improved by using a modified well-known dark-channel prior algorithm for removing nighttime haze, and then it uses α-automatic color equalization as post-processing for color correction over the entire image for getting a better enhanced output image free from haze with improved color constancy.

Bio-Medical Image Processing

The chapter focuses on application of digital image processing and deep learning for analyzing the occurrence of malaria from the medical reports. This approach is helpful in quick identification of the disease from the preliminary tests which are carried out in a person affected by malaria. The combination of deep learning has made the process much advanced as the convolutional neural network is able to gain deeper insights from the medical images of the person. Since traditional methods are not able to detect malaria properly and quickly, by means of convolutional neural networks, the early detection of malaria has been possible, and thus, this process will open a new door in the world of medical science.

A Performance Study of Image Quality Attributes on Smoothened Image Obtained by Anisotropic Diffusion-Based Models

Image acquisition systems usually acquire images with distortions due to various factors associated with digitization processes. Poisson is one of the common types of noises present in the image, and it distorts the fine features. Hence, it is necessary to denoise the noisy image by smoothing it to extract the features with fine details. Among the denoising methods, anisotropic diffusion method provides more adequate results. In this chapter, the authors dealt with existing models such as Perona-Malik (PM), total variation, Tsai, Chao, Chao TFT, difference eigen value PM, adaptive PM, modified PM, and Maiseli models. The performances of the models were tested on synthetic image added with the Poisson noise. Quality metrics are used to quantify and to ensure the smoothness of the resultant images. However, in order to ensure the completeness of the denoising effect, the qualitative attributes such as sharpness, blurriness, blockiness, edge quality, and false contouring are considered on smoothened images. The analysis results are shown the completeness of the denoising effect of the models.

Fatigue Monitoring for Drivers in Advanced Driver-Assistance System

The detection of person fatigue is one of the important tasks to detect drowsiness in the domain of image processing. Though lots of work has been carried out in this regard, there is a void of work shows the exact correctness. In this chapter, the main objective is to present an efficient approach that is a combination of both eye state detection and yawn in unconstrained environments. In the first proposed method, the face region and then eyes and mouth are detected. Histograms of Oriented Gradients (HOG) features are extracted from detected eyes. These features are fed to Support Vector Machine (SVM) classifier that classifies the eye state as closed or not closed. Distance between intensity changes in the mouth map is used to detect yawn. In second proposed method, off-the-shelf face detectors and facial landmark detectors are used to detect the features, and a novel eye and mouth metric is proposed. The eye results obtained are checked for consistency with yawn detection results in both the proposed methods. If any one of the results is indicating fatigue, the result is considered as fatigue. Second proposed method outperforms first method on two standard data sets.

A Review of Contemporary Image Compression Techniques and Standards

Uncompressed multimedia data such as images require huge storage space, processing power, transmission time, and bandwidth. In order to reduce the storage space, transmission time, and bandwidth, the uncompressed image data is compressed before its storage or transmission. This process not only permits a large number of images to be stored in a specified amount of storage space but also reduces the time required for them to be sent or download from the internet. In this chapter, the classification of an image on the basis of number of bits used to represent each pixel of the digital image and different types of image redundancies is presented. This chapter also introduced image compression and its classification into different lossless and lossy compression techniques along with their advantages and disadvantages. Further, discrete cosine transform, its properties, and the application of discrete cosine transform-based image compression method (i.e., JPEG compression model) along with its limitations are also discussed in detail.

Empirical Performance Analysis of Wavelet Transform Coding-Based Image Compression Techniques

In this chapter, the performance of wavelet transform-based EZW coding and SPIHT coding technique have been evaluated and compared in terms of CR, PSNR, and MSE by applying them to similar color images in two standard resolutions. The application of these techniques on entire color images such as passport size photograph in which the region containing the face of a person is more significant than other regions results in equal loss of information content and less compression ratio. So, to achieve the high CRs and distribute the quality of the image unevenly, this chapter proposes the ROI coding technique. Compressing ROI portion using discrete wavelet transform with Huffman coding and NROI compressed with Huffman, EZW coding, SPIHT coding suggested effective compression at nearly no loss of quality in the ROI portion of the photograph. Further, higher CR and PSNR with lower MSE have been found in high-resolution photographs, thereby permitting the reduction of storage space, faster transmission on low bandwidth channels, and faster processing.

An Edge Detection Approach for Fractal Image Processing

Research in the field of fractal image processing (FIP) has increased in the current era. Edge detection of fractal images can be considered as an important domain of research in FIP. Detecting edges in different fractal images accurate manner is a challenging problem in FIP. Several methods have introduced by different researchers to detect the edges of images. However, no method works suitably under all conditions. In this chapter, an edge detection method is proposed to detect the edges of gray scale and color fractal images. This method focuses on the quantitative combination of Canny, LoG, and Sobel (CLS) edge detection operators. The output of the proposed method is produced using matrix laboratory (MATLAB) R2015b and compared with the edge detection operators such as Sobel, Prewitt, Roberts, LoG, Canny, and mathematical morphological operator. The experimental outputs show that the proposed method performs better as compared to other traditional methods.

Analysis of Biomedical Image for Alzheimer's Disease Detection

Image analysis is giving a huge breakthrough in every field of science and technology. The image is just a collection of pixels and light intensity. The image capturing was done in two ways: (1) by using infrared sensors and (2) by using radiography. The normal images are captured by using the infrared sensors. Radiography uses the various forms of a light family, such as x-ray, gamma rays, etc., to capture the image. The study of neuroimaging is one of the challenging research topics in the field of biomedical image processing. So, from this note, the motivation for this work is to analyze 3D images to detect Alzheimer's disease and compare the statistical results of the whole brain image data with standard doctor's results. The authors also provide a very short implementation for brain slicing and feature extraction using Freesurfer and OpenNeuro dataset.

R-HOG Feature-Based Off-Line Odia Handwritten Character Recognition

Offline handwritten recognition system for Odia characters has received attention in the last few years. Although the recent research showed that there has been lots of work reported in different language, there is limited research carried out in Odia character recognition. Most of Odia characters are round in nature, similar in orientation and size also, which increases the ambiguity among characters. This chapter has harnessed the rectangle histogram-oriented gradient (R-HOG) for feature extraction method along with the principal component analysis. This gradient-based approach has been able to produce relevant features of individual ones in to the proposed model and helps to achieve high recognition rate. After certain simulations, the respective analysis of classifier shows that SVM performed better than quadratic. Among them, SVM produces with 98.8% and QC produces 96.8%, respectively, as recognition rate. In addition to it, the authors have also performed the 10-fold cross-validation to make the system more robust.