Mofakharul Islam

Unsupervised Color Textured Image Segmentation Using Cluster Ensembles and MRF Model

We propose a novel approach to implement robust unsupervised color image content understanding approach that segments a color image into its constituent parts automatically. The aim of this work is to produce precise segmentation of color images using color and texture information along with neighborhood relationships among image pixels which will provide more accuracy in segmentation. Here, unsupervised means automatic discovery of classes or clusters in images rather than generating the class or cluster descriptions from training image sets. As a whole, in this particular work, the problem we want to investigate is to implement a robust unsupervised SVFM model based color medical image segmentation tool using Cluster Ensembles and MRF model along with wavelet transforms for increasing the content sensitivity of the segmentation model. In addition, Cluster Ensemble has been utilized for introducing a robust technique for finding the number of components in an image automatically. The experimental results reveal that the proposed tool is able to find the accurate number of objects or components in a color image and eventually capable of producing more accurate and faithful segmentation and can. A statistical model based approach has been developed to estimate the Maximum a posteriori (MAP) to identify the different objects/components in a color image. The approach utilizes a Markov Random Field model to capture the relationships among the neighboring pixels and integrate that information into the Expectation Maximization (EM) model fitting MAP algorithm. The algorithm simultaneously calculates the model parameters and segments the pixels iteratively in an interleaved manner. Finally, it converges to a solution where the model parameters and pixel labels are stabilized within a specified criterion. Finally, we have compared our results with another well-known segmentation approach.

Real-time detection of children's skin on social networking sites using Markov random field modelling

Social networking sites are increasingly being used as the source for paedophiles to search for, download and exchange child exploitation images. Law Enforcement Agencies (LEAs) around the world face a difficult challenge to combat technologically-savvy paedophiles. In this paper, we propose a framework for detecting images containing childrens pictures in different poses, with the ultimate view of identifying and classifying images as corresponding to the COPINE scale. To achieve the goal of automatic detection, we present a novel stochastic vision model based on a Markov Random Fields (MRF) prior, which will employ a skin model and human affine-invariant geometric descriptor to detect and identify skin regions containing pornographic contexts.

Towards Automatic Image Segmentation Using Optimised Region Growing Technique

Image analysis is being adopted extensively in many applications such as digital forensics, medical treatment, industrial inspection, etc. primarily for diagnostic purposes. Hence, there is a growing interest among researches in developing new segmentation techniques to aid the diagnosis process. Manual segmentation of images is labour intensive, extremely time consuming and prone to human errors and hence an automated real-time technique is warranted in such applications. There is no universally applicable automated segmentation technique that will work for all images as the image segmentation is quite complex and unique depending upon the domain application. Hence, to fill the gap, this paper presents an efficient segmentation algorithm that can segment a digital image of interest into a more meaningful arrangement of regions and objects. Our algorithm combines region growing approach with optimised elimination of false boundaries to arrive at more meaningful segments automatically. We demonstrate this using X-ray teeth images that were taken for real-life dental diagnosis.

Illicit Image Detection Using Erotic Pose Estimation Based on Kinematic Constraints

With the advent of the Internet along with sophisticated digital image processing technology, the Internet quickly became the principal medium for the distribution of pornographic content favouring pornography to become a drug of the millennium. With the advent of GPRS mobile telephone networks, and with the large scale arrival of the 3G networks, along with the cheap availability of latest mobile sets and a variety of forms of wireless connections, the internet has already gone to mobile, drives us toward a new degree of complexity. The detection of pornography remains an important and significant research problem, since there is great potential to minimize harm to the community. In this paper, we propose a novel approach to investigate and implement a pornography detection technique towards a framework for automated detection of pornography based on most commonly found erotic poses. Compared to the results published in recent works, our proposed approach yields the highest accuracy in recognition.

Illicit Image Detection: An MRF Model Based Stochastic Approach

The steady growth of the Internet, sophisticated digital image processing technology, the cheap availability of storage devices and surfer’s ever-increasing interest on images have been contributing to make the Internet an unprecedented large image library. As a result, The Internet quickly became the principal medium for the distribution of pornographic content favouring pornography to become a drug of the millennium. With the arrival of GPRS mobile telephone technology, and with the large scale arrival of the 3G networks, along with the cheap availability of latest mobile sets and a variety of forms of wireless connections, the internet has already gone to mobile, driving us toward a new degree of complexity. In this paper, we propose a stochastic model based novel approach to investigate and implement a pornography detection technique towards a framework for automated detection of pornography based on contextual constraints that are representatives of actual pornographic activity. Compared to the results published in recent works, our proposed approach yields the highest accuracy in detection.

MRF model based unsupervised color textured image segmentation using Multidimensional Spatially Variant Finite Mixture Model

We investigate and propose a novel approach to implement an unsupervised color image segmentation model that segments a color image meaningfully and partitions into its constituent parts automatically. The aim is to devise a robust unsupervised segmentation approach that can segment a color textured image more accurately. Here, color and texture information of each individual pixel along with the spatial relationship within its neighborhood have been considered for producing more accuracy in segmentation. In this particular work, the problem we want to investigate is to implement a robust unsupervised Multidimensional Spatially Variant Finite Mixture Model (MSVFMM) based color image segmentation approach using Cluster Ensembles and MRF model along with Daubechies wavelet transforms for increasing the content sensitivity of the segmentation model in order to get a better accuracy in segmentation. Here, Cluster Ensemble has been utilized as a robust automatic tool for finding the number of components in an image. The main idea behind this work is introducing a Bayesian inference based approach to estimate the Maximum a Posteriori (MAP) to identify the different objects/components in a color image. Markov Random Field (MRF) plays a crucial role in capturing the relationships among the neighboring pixels. An Expectation Maximization (EM) model fitting MAP algorithm segments the image utilizing the pixel’s color and texture features and the captured neighborhood relationships among them. The algorithm simultaneously calculates the model parameters and segments the pixels iteratively in an interleaved manner. Finally, it converges to a solution where the model parameters and pixel labels are stabilized within a specified criterion. Finally, we have compared our results with another recent segmentation approach [10], which is similar in nature. The experimental results reveal that the proposed approach is capable of producing more accurate and faithful segmentation and can be employed in different practical image content understanding applications.

Stochastic Model Based Approach for Biometric Identification

In this paper, we present a new stochastic model based approach for enhanced image segmentation in biometric identification systems. Biometric features such as fingerprint, face, iris, hand geometry and more recently dental features are being used for human identification. Image analysis of each of these biometric features has various challenges to overcome. To address such contemporary problems of image segmentation, we provide a novel approach based on maximum a posteriori (MAP) fitting Gaussian mixture model using Expectation-Minimization (EM) algorithm within the Bayesian framework. Our new algorithm captures the pixel intensity by the likelihood term in Bayesian Networks, and a priori biasing term of the spatial location information with the help of Markov Random Fields (MRF) model. We have employed a novel approach of using Daubechies wavelet transform for texture feature extraction that uses MRF model and a robust technique of determining the number of pixel classes based on Cluster Ensembles for a reliable segmentation of dental X-ray images. We present how our approach could be applied in dental biometrics to achieve very fast and reliable human identification. Experiments show that our new unsupervised image segmentation technique provides accurate feature extraction and teeth segmentation for effective biometric identification.

Child face detection using age specific luminance invariant geometric descriptor

While considerable research have been conducted on age-wise age estimation using skin detection most often with other visual cues, relatively little research has looked closely at the subject. In this paper, we present a new framework for interpreting facial image patterns that can be employed in categorical age estimation. The aim is to propose a novel approach to investigate and implement a child face detection technique that is able to estimate age categorically — adult or child based on a new hybrid feature descriptor. The novel hybrid feature descriptor LIGD (the luminance invariant geometric descriptor) is composed of some low and high level features, which are found to be effective in characterizing the local appearance. In local appearance estimation, chromaticity, texture, and positional information of few facial visual cues can be employed simultaneously. Compared to the results published in a recent work, our proposed approach yields the highest precision and recall, and overall accuracy in recognition.

Unsupervised Segmentation of Industrial Images Using Markov Random Field Model

We propose a novel approach to investigate and implement unsupervised image content understanding and segmentation of color industrial images like medical imaging, forensic imaging, security and surveillance imaging, biotechnical imaging, biometrics, mineral and mining imaging, material science imaging, and many more. In this particular work, our focus will be on medical images only. The aim is to develop a computer aided diagnosis (CAD) system based on a newly developed Multidimensional Spatially Variant Finite Mixture Model (MSVFMM) using Markov Random Fields (MRF) Model. Unsupervised means automatic discovery of classes or clusters in images rather than generating the class or cluster descriptions from training image sets. The aim of this work is to produce precise segmentation of color medical images on the basis of subtle color and texture variation. Finer segmentation of images has tremendous potential in medical imaging where subtle information related to color and texture is required to analyze the image accurately. In this particular work, we have used CIE-Luv and Daubechies wavelet transforms as color and texture descriptors respectively. Using the combined effect of a CIE-Luv color model and Daubechies transforms, we can segment color medical images precisely in a meaningful manner. The evaluation of the results is done through comparison of the segmentation quality with another similar alternative approach and it is found that the proposed approach is capable of producing more faithful segmentation.

A New Stochastic Model Based Approach for Object Identification and Segmentation in Textured Color Image

We investigate and propose a novel stochastic model based approach to implement a robust unsupervised color image content understanding technique that segments a color textured image into its constituent parts automatically and meaningfully. The aim of this work is to detection and identification of different objects in a color image using image segmentation. Image segments or objects are produced using precise color information, texture information and neighborhood relationships among neighboring image pixels. As a whole, in this particular work, the problem we want to investigate is to implement a robust Maximum a posteriori (MAP) based unsupervised color textured image segmentation approach using Cluster Ensembles, MRF model and Daubechies wavelet transform for identification and segmentation of image contents or objects. In addition,Cluster Ensemble has been utilizedfor introducing a robust technique for finding the number of components in an image automatically. The experimental results reveal that the proposed model is able to find the accurate number of objects or components in a color image and can produce more accurate and faithful segmentation of different meaningful objects from relatively complex background. Finally, we have compared our results with another similar existing segmentation approach.