Vibhav Prakash Singh

An efficient content based image retrieval for normal and abnormal mammograms

Diagnosis of breast cancer from mammograms is a crucial task. CBIR can support radiologists in their decision to retrieve similar mammograms out of a database to compare the past cases with current case. Pectoral muscle, labels, and artifacts, present in mammograms can bias the detection procedures. So extractions of these are an essential preprocessing step in the process of CAD. In this paper, an efficient content based image retrieval system is developed for normal and abnormal classes of mammograms. The pre-processing steps include are artifact suppression using CCL and Morphological operation, automatic pectoral muscle removal, and image enhancement using CLAHE. After pre-processing, we segment images using modified region growing algorithm, and using this segmented image, Histogram based statistical, Shape, Wavelet and Gabor features are extracted. Finally, images are retrieved using Euclidean distance similarity measure. Experiments on benchmark database confirm that the proposed segmentation and retrieval framework performs, encouraging than Fuzzy c mean, Ostu, and Region Growing based segmentation and retrieval approaches.

Effective mammogram classification based on center symmetric-LBP features in wavelet domain using random forests

Mammogram classification is a crucial and challenging problem, because it helps in early diagnosis of breast cancer and supports radiologists in their decision to analyze similar mammograms out of a database by recognizing the classes of current mammograms. This paper proposes an effective method for classifying mammograms using random forests with wavelet based center-symmetric local binary pattern (WCS-LBP). To classify mammograms, multi-resolution CS-LBP texture characteristics from non-overlapping regions of the mammograms are captured. Further, we examine most relevant features using support vector machine-recursive feature elimination (SVM-RFE). Finally, we feed the selected features to decision trees and construct random forests which are an ensemble of random decision trees. Using wavelet based local CS-LBP features with random forest, we classify the test images into different categories having the maximum posterior probability. The proposed method shows the improved performance as compared with other variant features and state-of-art methods. The obtained performance measures are 97.3% accuracy, 97.3% precision, 97.2% recall, 97.2% F-measure and 94.1% Matthews correlation coefficient (MCC).

Design & performance analysis of content based image retrieval system based on image classification usingvarious feature sets

With the rapid advancement of digital imaging technologies, and the use of large volume image databases in various applications, it becomes imperative to build an automatic and an efficient image retrieval system. Content Based Image Retrieval (CBIR) is most emerging and vivid research area in computer vision, in which unknown query image assigns to the closest possible similar images available in the database. Current systems mainly use colour, texture, and shape information for image retrieval using similarity measures between query and database images features. Here this work, proposed a classification system that allows recognizing and recovering the class of a query image based on its visual content. This successful categorization of images greatly enhances the performance of retrieval by filtering out irrelevant classes. In this way we have done the comparative analysis of various features as an individual or in combinations, with direct similarity measure and proposed framework. Experiments on benchmark Wang database show that the proposed classification & retrieval framework performs significantly better than the common framework of distances.

Content-based mammogram retrieval using k-means clustering and local binary pattern

Early diagnosis of breast cancer can improve the survival rate by detecting cancer at initial stage. In this paper, an efficient computer-based mammogram retrieval system is proposed, which helps in early diagnosis of breast cancer by comparing the current case with past cases. The proposed steps include cropping of mammograms, feature extraction using local binary pattern (LBP) and k-mean clustering. Using LBP, k-mean generates the clusters based on the visual similarity of mammograms. Further, query image features are matched with all cluster representatives to find the closest cluster. Finally, images are retrieved from this closest cluster using Euclidean distance similarity measure. So, at the searching time the query image is searched only in small subset depending upon cluster size and is not compared with all the images in the database, reflects a superior response time with good retrieval performances. Experiments on benchmark mammography image analysis society (MIAS) database confirm the effectiveness of this work.

Automated digital mammogram segmentation using Dispersed Region Growing and Sliding Window Algorithm

Early diagnosis of breast cancer can improve the survival rate by detecting cancer at an early stage. Breast region segmentation is an essential step in the analysis of digital mammograms. Accurate image segmentation leads to better detection of cancer. It aims at separating out Region of Interest (ROI) from rest of the image. The procedure begins with removal of labels, annotations and tags from the mammographic image using morphological opening method. Sliding Window Algorithm (SWA) is used for removal of pectoral muscle from mammograms which is necessary as the intensity values of pectoral muscles are similar to that of ROI which makes it difficult to separate out. After removing the pectoral muscle, Dispersed Region Growing Algorithm (DRGA) is used for segmentation of mammogram which disperses seeds in different regions instead of a single bright region. To demonstrate the validity of our segmentation method, 322 mammographic images from Mammographic Image Analysis Society (MIAS) database are used. The dataset contains mediolateral oblique (MLO) view of mammograms. Experimental results on MIAS dataset show the effectiveness of our proposed method.

An Efficient Image Retrieval Based on Fusion of Fast Features and Query Image Classification

Content Based Image Retrieval (CBIR) is an emerging research area in computer vision, in which, we yield similar images as per the query content. For the implementation of CBIR system, feature extraction plays a vital role, where colour feature is quite remarkable. But, due to unevenly colored or achromatic surfaces, the role of texture is also important. In this paper, an efficient and fast CBIR system is proposed, which is based on a fusion of computationally light weighted colour and texture features; chromaticity moment, colour percentile, and local binary pattern (LBP). Using these features with multiclass classifier, the authors propose a supervised query image classification and retrieval model, which filters all irrelevant class images. Basically, this model categorizes and recovers the class of a query image based on its visual content, and this successful classification of image significantly enhances the performance and searching time of retrieval system. Descriptive experimental analysis on benchmark databases confirms the effectiveness of proposed retrieval framework. KEywoRDS Chromaticity Moment, Classification, Content Based Image Retrieval, Feature Extraction, Similarity Measure

Improved image retrieval using color-invariant moments

Content-based image retrieval (CBIR) is growing research field in computer vision in which, we retrieve images that are visually relevant to the query. As we know that, CBIR system requires low-level descriptors, and many different methods have been recently proposed using color, texture, and shape based descriptors. Some of these methods use the histogram or some variation for representing color which may require a significant amount of similarity calculation and space. This paper uses L2 similarity measure on small dimension of hybrid color and shape features. i.e include Euclidean distance as L2 measure, color moment as color feature and invariant moment as a shape feature. From the descriptive analysis on benchmark Wang database, it is observed that proposed hybrid feature with L2 similarity measure performed significantly encouraging. For 20 number of retrieved images, it gives 66.2% mean-average precision and 13.24 % mean-average recall.

Automated and effective content-based image retrieval for digital mammography

Nowadays, huge number of mammograms has been generated in hospitals for the diagnosis of breast cancer. Content-based image retrieval (CBIR) can contribute more reliable diagnosis by classifying the query mammograms and retrieving similar mammograms already annotated by diagnostic descriptions and treatment results. Since labels, artifacts, and pectoral muscles present in mammograms can bias the retrieval procedures, automated detection and exclusion of these image noise patterns and/or non-breast regions is an essential pre-processing step. In this study, an efficient and automated CBIR system of mammograms was developed and tested. First, the pre-processing steps including automatic labelling-artifact suppression, automatic pectoral muscle removal, and image enhancement using the adaptive median filter were applied. Next, pre-processed images were segmented using the co-occurrence thresholds based seeded region growing algorithm. Furthermore, a set of image features including shape, histogram based statistical, Gabor, wavelet, and Gray Level Co-occurrence Matrix (GLCM) features, was computed from the segmented region. In order to select the optimal features, a minimum redundancy maximum relevance (mRMR) feature selection method was then applied. Finally, similar images were retrieved using Euclidean distance similarity measure. The comparative experiments conducted with reference to benchmark mammographic images analysis society (MIAS) database confirmed the effectiveness of the proposed work concerning average precision of 72% and 61.30% for normal & abnormal classes of mammograms, respectively.

Combining hybrid information descriptors and DCT for improved CBIR performance

Content Based Image Retrieval (CBIR) aims to retrieves images in the database that are similar to a query image based on the contents of the image rather than metadata. The algorithm used to extract features from images is one of the most influential factors towards a CBIR systems performance. In this paper, we take a look at hybrid information descriptors (HID) as the feature extraction algorithm for our CBIR system and supplement HID with information in the compressed domain using discrete cosine transform (DCT). The HID+DCT algorithm proposed was compared with the HID algorithm on the Corel Dataset. We found out that the HID+DCT algorithm performs better than HID algorithm. We have used and compared Manhattan Distance and Euclidian Distance as distance metrics during the process of feature matching and observed that Manhattan Distance gave the best precision value for HID+DCT feature. However, the use of DCT results in a larger feature vector size which could potentially lead to slow queries. We consider using minimal-redundancy-maximal-relevance criterion (mRMR) for feature selection to reduce the size of feature vector to avoid speed related issues. We observe that the difference in precision for a feature vector reduced to almost the same size as HIDs feature vector and HID+DCT is negligible.

Improved Content-Based Image Classification Using a Random Forest Classifier

Content-based image classification is being one of the important phase in the process of automatic retrieval and annotation of images. In this paper, we are focused on effective image classification using low-level colour and texture features. It is well proved that the classifier performances are good for the unknown images, if quite similar images are present in the training set. On the other hand, classifier performances could not be guaranteed for images that are very much dissimilar from training set. This generalization problem of classifier can bias the image retrieval and annotation process. This paper objective is to investigate the discrimination abilities for such different class standard images. For improved image classification, we extract the effective low-level colour and texture features from the images. These features include; local binary pattern (LBP) based texture features, and colour percentile, colour moment, and colour histogram based colour features. To overcome the generalization problem, we have used random forest classifier, capable for handle over-fitting situation. Experimental analysis on benchmark database confirms the effectiveness of this work.