T Jyothirmayi

Bio: T Jyothirmayi is an academic researcher from Gandhi Institute of Technology and Management. The author has contributed to research in topics: Image segmentation & Segmentation-based object categorization. The author has an hindex of 2, co-authored 3 publications receiving 7 citations.

Image Segmentation Based on Doubly Truncated Generalized Laplace Mixture Model and K Means Clustering

Abstract: The present paper aims at performance evaluation of Doubly Truncated Generalized Laplace Mixture Model and K-Means clustering (DTGLMM-K) for image analysis concerned to various practical applications like security, surveillance, medical diagnostics and other areas. Among the many algorithms designed and developed for image segmentation the dominance of Gaussian Mixture Model (GMM) has been predominant which has the major drawback of suiting to a particular kind of data. Therefore the present work aims at development of DTGLMM-K algorithm which can be suitable for wide variety of applications and data. Performance evaluation of the developed algorithm has been donethrough various measures like Probabilistic Rand index (PRI), Global Consistency Error (GCE) and Variation of Information (VOI). During the current work case studies forvarious different images having pixel intensities has been carried out and the obtained results indicate the superiority of the developed algorithm for improved image segmentation.

Performance Evaluation of Image Segmentation Method based on Doubly Truncated Generalized Laplace Mixture Model and Hierarchical Clustering

Abstract: The present paper aims at performance evaluation of Doubly Truncated Generalized Laplace Mixture Model and Hierarchical clustering (DTGLMMH) for image analysis concerned to various practical applications like security, surveillance, medical diagnostics and other areas. Among the many algorithms designed and developed for image segmentation the dominance of Gaussian Mixture Model (GMM) has been predominant which has the major drawback of suiting to a particular kind of data. Therefore the present work aims at development of DTGLMM-H algorithm which can be suitable for wide variety of applications and data. Performance evaluation of the developed algorithm has been done through various measures like Probabilistic Rand index (PRI), Global Consistency Error (GCE) and Variation of Information (VOI). During the current work case studies for various different images having pixel intensities has been carried out and the obtained results indicate the superiority of the developed algorithm for improved image segmentation.

Studies on Image Segmentation Integrating Generalized Laplace Mixture Model and Hierarchical Clustering

Abstract: In many practical applications such as security and surveillance, robotics, medical diagnostics, remote sensing, video processing the image segmentation plays a dominant role. In general the image segmentation is performed either hierarchical method or model based methods. Both methods have advantages and disadvantages. Integrating these two methods will provide efficient utilization of resources and increases segmentation performance. Hence, in this paper an image segmentation method based on generalized Laplace Mixture Model integrated with hierarchical clustering method was developed and analyzed. The updated equations for estimating the model parameters using EM algorithm are derived for the generalized Laplace Mixture Model for the first time. The segmentation algorithm is presented under component maximum likelihood with Bayesian criteria. The efficiency of the proposed algorithm is validated by selecting sample images from Berkeley image data set and computing the segmentation performance measures such as GCE, PRI and VOI. A comparative study of proposed algorithm with that of model based image segmentation algorithm on GMM revealed that the proposed algorithm outperforms the existing ones. General Terms Image segmentation, Gaussian distribution, EM algorithm.

Recognition of Wheat Spike from Field Based Phenotype Platform Using Multi-Sensor Fusion and Improved Maximum Entropy Segmentation Algorithms

Abstract: To obtain an accurate count of wheat spikes, which is crucial for estimating yield, this paper proposes a new algorithm that uses computer vision to achieve this goal from an image. First, a home-built semi-autonomous multi-sensor field-based phenotype platform (FPP) is used to obtain orthographic images of wheat plots at the filling stage. The data acquisition system of the FPP provides high-definition RGB images and multispectral images of the corresponding quadrats. Then, the high-definition panchromatic images are obtained by fusion of three channels of RGB. The Gram–Schmidt fusion algorithm is then used to fuse these multispectral and panchromatic images, thereby improving the color identification degree of the targets. Next, the maximum entropy segmentation method is used to do the coarse-segmentation. The threshold of this method is determined by a firefly algorithm based on chaos theory (FACT), and then a morphological filter is used to de-noise the coarse-segmentation results. Finally, morphological reconstruction theory is applied to segment the adhesive part of the de-noised image and realize the fine-segmentation of the image. The computer-generated counting results for the wheat plots, using independent regional statistical function in Matlab R2017b software, are then compared with field measurements which indicate that the proposed method provides a more accurate count of wheat spikes when compared with other traditional fusion and segmentation methods mentioned in this paper.

Identifying the presence of bacteria on digital images by using asymmetric distribution with k-means clustering algorithm.

Abstract: This paper is mainly aimed at the decomposition of image quality assessment study by using Three Parameter Logistic Mixture Model and k-means clustering (TPLMM-k). This method is mainly used for the analysis of various images which were related to several real time applications and for medical disease detection and diagnosis with the help of the digital images which were generated by digital microscopic camera. Several algorithms and distribution models had been developed and proposed for the segmentation of the images. Among several methods developed and proposed, the Gaussian Mixture Model (GMM) was one of the highly used models. One can say that almost the GMM was playing the key role in most of the image segmentation research works so far noticed in the literature. The main drawback with the distribution model was that this GMM model will be best fitted with a kind of data in the dataset. To overcome this problem, the TPLMM-k algorithm is proposed. The image decomposition process used in the proposed algorithm had been analyzed and its performance was analyzed with the help of various performance metrics like the Variance of Information (VOI), Global Consistency Error (GCE) and Probabilistic Rand Index (PRI). According to the results, it is shown that the proposed algorithm achieves the better performance when compared with the previous results of the previous techniques. In addition, the decomposition of the images had been improved in the proposed algorithm.

Parametric Comparison of K-means and Adaptive K-means Clustering Performance on Different Images

Abstract: Image segmentation takes a major role to analyzing the area of interest in image processing. Many researchers have used different types of techniques to analyzing the image. One of the widely used techniques is K-means clustering. In this paper we use two algorithms K-means and the advance of K-means is called as adaptive K-means clustering. Both the algorithms are using in different types of image and got a successful result. By comparing the Time period, PSNR and RMSE value from the result of both algorithms we prove that the Adaptive K-means clustering algorithm gives a best result as compard to K-means clustering in image segmentation.

The Role of Hybrid Classifiers in Problems of Chest Roentgenogram Classification

Abstract: The hybrid technology of chest roentgenogram classification, based on three-level hierarchic structure, has been suggested. “Weak classifiers,” based on two ways of data analysis, are formed on the first level. The approach is to make a “weak” classifier using the first way which is based on the analysis of Fourier amplitude spectra in sliding window. An X-ray image is sequentially scanned by windows of various scales. A “weak” classifier is made based on Fourier amplitude spectrum, defined in each window. It refers to an image segment, which got into the sliding window, to a certain class. The second way of making a “weak” classifier is based on the descriptors, which were received because of intensity histogram approximation in the analysis window. The number of received “weak classifiers,” based on the two ways of analysis, depends on the number of analysis window scales chosen. On the second hierarchic level, the solutions of “weak” classifiers within every way of the first hierarchic-level analysis are integrated. A final classifier makes the ultimate solution, which aggregates the solutions of two second hierarchical level classifiers.