Image segmentation is a challenging process in numerous applications. Region growing is one of the segmentation techniques as a basis for the Seeded Region Growing method. A novel real time integrated method was developed in the current work to locate the segmented region of interest of an image based on the Region Growing segmentation method along with the thresholding supported image segmentation. Through the proposed work, a homogeneity based on pixel intensity was suggested as well as the threshold value can be decided via a variety of schemes such as manual selection, Iterative method, Otsu’s method, local thresholding to obtain the best possible threshold. The experimental results were performed on different images obtained from an Alpert dataset. A comparative study was arried out with the human segmented image, threshold based region growing, and the proposed integrated method. The results established that the proposed integrated method outperformed the region growing method in terms of the recall and F-score. Although, it had comparable recall values with that gained by the human segmented images. It was noted that as the image under test had a dark background with the brighter object, thus the proposed method provided the superior recall value compared to the other methods.

http://ijece.iaescore.com/index.php/IJECE/article/download/5889/5549

An Integrated Interactive Technique for Image Segmentation using Stack based Seeded Region Growing and Thresholding

Prediction of human diseases using optimized clustering techniques

Urban impervious surface (UIS) offers potentially valuable information for the development of sustainable urban management strategies and environmental change monitoring actions. In this article, we focus on UIS-detection-related issues, identify and analyze systematic challenges, construct a general processing scheme for UIS detection, provide four categories of major methods, and propose a deep compressive-based convolutional deep belief network (dc-CDBN) method and a novel classification strategy for multisource data fusion models.

Urban Impervious Surface Detection From Remote Sensing Images: A review of the methods and challenges

Inspired by the ability of $$\ell _p$$ l p -regularized algorithms and the close connection of total variation (TV) to the $$\ell _1$$ l 1 norm, a $$p$$ p th-power type TV denoted as TV $$_p$$ p is proposed for $$0\le p \le 1$$ 0 ≤ p ≤ 1 . The TV $$_p$$ p -regularized problem for image denoising is nonconvex thus difficult to tackle directly. Instead, we deal with the problem by proposing a weighted TV (WTV) minimization where the weights are updated iteratively to locally approximate the TV $$_p$$ p -regularized problem. The difficulty of WTV minimization is dealt with in a modified split Bregman framework. Numerical results are presented to demonstrate improved denoising performance of the new algorithm with $$p<1$$ p < 1 relative to that obtained by the standard TV minimization and several recent denoising methods from the literature on a variety of images.

Image denoising by generalized total variation regularization and least squares fidelity

This Research was conducted to analyze the identification of eggs. The research processes use two tools, namely thermal imaging camera and smartphone camera. The identification process was done by using Matlab prototype tools. The image has been acquired by means of proficiency level, then analyzed and applied several methods. Image acquisition results of thermal imaging camera are processed using morphological dilation and do the complement in black and white (BW). While the digital image uses the merger method of morphological dilation and opening, and it doesn't need to be complemented. Labeling process is done, and the process of determining centroid and bounding box. The process has been done and it can be applied for identifying of chicken eggs with the accuracy rate of 100%. There are different methods of both images is obtained area (pixels) which is equivalent to the difference is very small as 6 x 10 -3 .

/pdf/identity-analysis-of-egg-based-on-digital-and-thermal-4zvswss7ed.pdf

Identity Analysis of Egg Based on Digital and Thermal Imaging: Image Processing and Counting Object Concept

This paper introduces the concept of image fusion of filtered noisy images for impulse noise reduction. Image fusion is the process of combining two or more images into a single image while retaining the important features of each image. Multiple image fusion is an important technique used in military, remote sensing and medical applications. Five different filtering algorithms are used individually for filtering the image captured from the sensor. The filtered images are fused to obtain a high quality image compared to individually denoised images. In-order to better appraise the noise cancellation behavior of our fusion technique from the point of view of human perception, an edge detection is performed using canny filter for the fused image. Experimental results show that this method is capable of producing better results compared to individually denoised images.

/pdf/impulse-noise-removal-in-digital-images-51n5jvevcw.pdf

Impulse Noise Removal in Digital Images

Microarray technology allows the simultaneous monitoring of thousands of genes. Based on the gene expression measurements, microarray technology have proven powerful in gene expression profiling for discovering new types of diseases and for predicting the type of a disease. Gridding, segmentation and intensity extraction are the three important steps in microarray image analysis. Clustering algorithms have been used for microarray image segmentation with an advantage that they are not restricted to a particular shape and size for the spots. Instead of using single feature clustering algorithm, this paper presents multiple feature clustering algorithm with three features for each pixel such as pixel intensity, distance from the center of the spot and median of surrounding pixels. In all the traditional clustering algorithms, number of clusters and initial centroids are randomly selected and often specified by the user.  In this paper, a new algorithm based on empirical mode decomposition algorithm for the histogram of the input image will generate the number of clusters and initial centroids required for clustering.   It overcomes the shortage of random initialization in traditional clustering and achieves high computational speed by reducing the number of iterations. The experimental results show that multiple feature Fuzzy C-means has segmented the microarray image more accurately than other algorithms.

/pdf/multiple-feature-fuzzy-c-means-clustering-algorithm-for-j0oezahc8h.pdf

Multiple Feature Fuzzy c-means Clustering Algorithm for Segmentation of Microarray Images

A Deoxyribonucleic Acid (DNA) microarray is a collection of microscopic DNA spots attached to a solid surface, such as glass, plastic or silicon chip forming an array. The analysis of DNA microarray images allows the identification of gene expressions to draw biological conclusions for applications ranging from genetic profiling to diagnosis of cancer. The DNA microarray image analysis includes three tasks: gridding, segmentation and intensity extraction. Clustering algorithms have been applied for segmenting the microarray image. Among these approaches, K-Means method is simple one. However, microarray image contains noise and the noise would affect the segmentation results. In this paper, we propose to combine the K-means method with Bi-dimensional Empirical Mode Decomposition for segmenting the microarray image in order to reduce the effect of noise. We call this method as K-Means with Bi-dimensional Empirical Mode decomposition (KBEMD). Using the KBEMD method on microarray image, we obtain better results than those using K-Means only. Using the KBEMD method to analyze microarray image can save time and obtain more reasonable results.

K-Means with Bi-dimensional Empirical Mode Decomposition for segmentation of microarray image

Spot Edge Detection in Microarray Images Using Bi-Dimensional Empirical Mode Decomposition

Nowadays, huge data bases are required to store the Digital medical images so that they can be accessed easily on requirement. To retrieve the diagnostic images, radiologist and physicians are using Content based image retrieval (CBIR). Algorithms extract features like texture, edge, color and shape from an image in CBIR systems and these extracted features from the input and are compared for similarity with the features of images in database. In this paper, Lossless compression is used for storage and effective transmission in inadequate bandwidth. Visually lossless image compression is obtained using the Daubechies wavelet with Huffman coding. Gabor transforms are utilized to extract the shape and texture features from the images. Features are selected with Mutual Information (MI) and the proposed wrapper based Cuckoo Search (CS) technique. Extracted features are fed as input to the proposed partial Recurrent Neural Networks (RNN) for the classification. The network is optimized hybrid Particle Swarm Optimization and Cuckoo Search. It was observed that the classification accuracy acquired is satisfactory

J. Harikiran

Papers

Impulse Noise Removal in Digital Images

Multiple Feature Fuzzy c-means Clustering Algorithm for Segmentation of Microarray Images

K-Means with Bi-dimensional Empirical Mode Decomposition for segmentation of microarray image

Spot Edge Detection in Microarray Images Using Bi-Dimensional Empirical Mode Decomposition

A Novel Approach for Feature Selection and Classifier Optimization Compressed Medical Retrieval Using Hybrid Cuckoo Search