Mohammad Faizal Ahmad Fauzi

An integrated content and metadata based retrieval system for art

A new approach to image retrieval is presented in the domain of museum and gallery image collections. Specialist algorithms, developed to address specific retrieval tasks, are combined with more conventional content and metadata retrieval approaches, and implemented within a distributed architecture to provide cross-collection searching and navigation in a seamless way. External systems can access the different collections using interoperability protocols and open standards, which were extended to accommodate content based as well as text based retrieval paradigms. After a brief overview of the complete system, we describe the novel design and evaluation of some of the specialist image analysis algorithms, including a method for image retrieval based on sub-image queries, retrievals based on very low quality images and retrieval using canvas crack patterns. We show how effective retrieval results can be achieved by real end-users consisting of major museums and galleries, accessing the distributed, but integrated, digital collections.

Segmentation of CT Brain Images Using K-Means and EM Clustering

The combination of the different approaches for the segmentation of brain images is presented in this paper. The system segments the CT head images into 3 clusters, which are abnormal regions, cerebrospinal fluid (CSF) and brain matter. Firstly we filter out the abnormal regions from the intracranial area by using the decision tree. As for the segmentation of the CSF and brain matter, we employed the expectation-maximization (EM) algorithm. The system has been tested with a number of real CT head images and has achieved some promising results.

Segmentation of CT Brain Images Using Unsupervised Clusterings

In this paper, we present non-identical unsupervised clustering techniques for the segmentation of CT brain images. Prior to segmentation, we enhance the visualization of the original image. Generally, for the presence of abnormal regions in the brain images, we partition them into 3 segments, which are the abnormal regions itself, the cerebrospinal fluid (CSF) and the brain matter. However, for the absence of abnormal regions in the brain images, the final segmented regions will consist of CSF and brain matter only. Therefore, our system is divided into two stages of clustering. The initial clustering technique is for the detection of the abnormal regions. The later clustering technique is for the segmentation of the CSF and brain matter. The system has been tested with a number of real CT head images and has achieved satisfactory results.

Comparison of different feature extraction techniques in content-based image retrieval for CT brain images

Content-based image retrieval (CBIR) system helps users retrieve relevant images based on their contents. A reliable content-based feature extraction technique is therefore required to effectively extract most of the information from the images. These important elements include texture, colour, intensity or shape of the object inside an image. CBIR, when used in medical applications, can help medical experts in their diagnosis such as retrieving similar kind of disease and patientpsilas progress monitoring. In this paper, several feature extraction techniques are explored to see their effectiveness in retrieving medical images. The techniques are Gabor transform, discrete wavelet frame, Hu moment invariants, Fourier descriptor, gray level histogram and gray level coherence vector. Experiments are conducted on 3,032 CT images of human brain and promising results are reported.

Automatic texture segmentation for content-based image retrieval application

In this article, a brief review on texture segmentation is presented, before a novel automatic texture segmentation algorithm is developed. The algorithm is based on a modified discrete wavelet frames and the mean shift algorithm. The proposed technique is tested on a range of textured images including composite texture images, synthetic texture images, real scene images as well as our main source of images, the museum images of various kinds. An extension to the automatic texture segmentation, a texture identifier is also introduced for integration into a retrieval system, providing an excellent approach to content-based image retrieval using texture features.

A multiscale approach to texture-based image retrieval

This paper presents research on a robust technique for texture-based image retrieval in multimedia museum collections. The aim is to be able to use a query image patch containing a single texture to retrieve images containing an area with similar texture to that in the query. The feature extractor used to build the feature vectors is based on an improved version of the discrete wavelet frames (DWF), proposed elsewhere. In order to utilise the feature extractor on real scene image datasets, a block-oriented decomposition technique, termed the multiscale sub-image matching method, is presented. The multiscale method, together with the DWF, provide an efficient content-based retrieval technique without the need for segmentation. The algorithms are tested on a range of databases of texture images as well as on real museum image collections. Promising results are reported.

A Fully Unsupervised Texture Segmentation Algorithm

This paper presents a fully unsupervised texture segmentation algorithm by using a modified discrete wavelet frames decomposition and a mean shift algorithm. By fully unsupervised, we mean the algorithm does not require any knowledge of the type of texture present nor the number of textures in the image to be segmented. The basic idea of the proposed method is to use the modified discrete wavelet frames to extract useful information from the image. Then, starting from the lowest level, the mean shift algorithm is used together with the fuzzy c-means clustering to divide the data into an appropriate number of clusters. The data clustering process is then refined at every level by taking into account the data at that particular level. The final crispy segmentation is obtained at the root level. This approach is applied to segment a variety of composite texture images into homogeneous texture areas and very good segmentation results are reported.

Computerized segmentation and measurement of chronic wound images

An estimated 6.5 million patients in the United States are affected by chronic wounds, with more than US

Texture-based Image Retrieval Using Multiscale Sub-image Matching

25 billion and countless hours spent annually for all aspects of chronic wound care. There is a need for an intelligent software tool to analyze wound images, characterize wound tissue composition, measure wound size, and monitor changes in wound in between visits. Performed manually, this process is very time-consuming and subject to intra- and inter-reader variability. In this work, our objective is to develop methods to segment, measure and characterize clinically presented chronic wounds from photographic images. The first step of our method is to generate a Red-Yellow-Black-White (RYKW) probability map, which then guides the segmentation process using either optimal thresholding or region growing. The red, yellow and black probability maps are designed to handle the granulation, slough and eschar tissues, respectively; while the white probability map is to detect the white label card for measurement calibration purposes. The innovative aspects of this work include defining a four-dimensional probability map specific to wound characteristics, a computationally efficient method to segment wound images utilizing the probability map, and auto-calibration of wound measurements using the content of the image. These methods were applied to 80 wound images, captured in a clinical setting at the Ohio State University Comprehensive Wound Center, with the ground truth independently generated by the consensus of at least two clinicians. While the mean inter-reader agreement between the readers varied between 67.4% and 84.3%, the computer achieved an average accuracy of 75.1%.

Segmentation of CT Head Images

The paper presents research on a robust technique for texture-based image retrieval in multimedia museum collections. The aim is to be able to use a query image patch containing a single texture to retrieve images containing some area with similar texture to that in the query. A retrieval technique without the need for segmentation is presented. The algorithm uses a multiscale sub-image matching method together with an appropriate texture feature extractor. The multiscale sub-image matching is achieved by first decomposing each database image into a set of 64×64 pixel patches covering the entire image. The resolution of the database image is then rescaled to create sub-images corresponding to a larger scale. The process continues until the final resolution of the image is equal to some pre-determined value. Finally, a collection of sub-images corresponding to different image regions and scales is obtained. The final image feature vector consists of a collection of feature vectors corresponding to each sub-image. Several wavelet-based feature extractors are tested with the multiscale technique. From the experiments, it is found that the multiscale sub-image matching method is an efficient way to achieve effective texture retrieval without any need for segmentation.