Kent K. T. Cheung

Symmetry detection by generalized complex (GC) moments: a close-form solution

This paper presents a unified method for detecting both reflection-symmetry and rotation-symmetry of 2D images based on an identical set of features, i.e., the first three nonzero generalized complex (GC) moments. This method is theoretically guaranteed to detect all the axes of symmetries of every 2D image, if more nonzero GC moments are used in the feature set. Furthermore, we establish the relationship between reflectional symmetry and rotational symmetry in an image, which can be used to check the correctness of symmetry detection. This method has been demonstrated experimentally using more than 200 images.

3D head model classification by evolutionary optimization of the Extended Gaussian Image representation

Classification of 3D head models based on their shape attributes for subsequent indexing and retrieval are important in many applications, as in hierarchical content-based retrieval of these head models for virtual scene composition, and the automatic annotation of these characters in such scenes. While simple feature representations are preferred for more efficient classification operations, these features may not be adequate for distinguishing between the subtly different head model classes. In view of these, we propose an optimization approach based on genetic algorithm (GA) where the original model representation is transformed in such a way that the classification rate is significantly enhanced while retaining the efficiency and simplicity of the original representation. Specifically, based on the Extended Gaussian Image (EGI) representation for 3D models which summarizes the surface normal orientation statistics, we consider these orientations as random variables, and proceed to search for an optimal transformation for these variables based on genetic optimization. The resulting transformed distributions for these random variables are then used as the modified classifier inputs. Experiments have shown that the optimized transformation results in a significant improvement in classification results for a large variety of class structures. More importantly, the transformation can be indirectly realized by bin removal and bin count merging in the original histogram, thus retaining the advantage of the original EGI representation.

Indexing and retrieval of 3D models by unsupervised clustering with hierarchical SOM

A hierarchical indexing structure for 3D model retrieval based on the hierarchical self organizing map (HSOM) is proposed. The proposed approach organizes the database into a hierarchy so that head models are partitioned by coarse features initially and finer scale features are used in lower levels. The aim is to traverse a small subset of the database during retrieval. This is made possible by exploiting the multi-resolution capability of spherical wavelet features to successively approximate the salient characteristics of the head models, which are encoded in the form of weight vectors associated with the nodes at different levels (from coarse to fine) of the HSOM. To avoid premature commitment to a possibly erroneous model class, search is propagated from a subset of nodes at each level, which is selected based on a fuzzy membership measure between the query feature vector and weight vector, instead of taking the winner-take-all approach. Experiments show that, in addition to efficiency improvement, model retrieval based on the HSOM approach is able to achieve a much higher accuracy compared with the case where no indexing is performed.

A multi-window approach to classify histological features

Medical images are usually composed of different kinds of texture components which are always so much varied that a conventional single window approach cannot capture enough salient information for comparison. This paper applies the widely used multi-channel Gabor filters to demonstrate how a multi-window approach can improve the classification accuracy rate of histological labels. In addition, a most confident window method is proposed to further increase the accuracy rate of the multi-window approach.

An evolutionary optimization approach for 3D human head model classification

Classification of 3-D head models based on their shape attributes for subsequent indexing and retrieval are important in many applications, as in the selection and generation of human characters in virtual scenes, and the composition of morphing sequences requiring a qualitatively similar target head model. Simple feature representations are more efficient but may not be adequate for distinguishing the subtly different head model classes. In view of these, we propose an optimization approach based on genetic algorithm (GA) where the original model representation is transformed in such a way that the classification rate is significantly enhanced while retaining the efficiency and simplicity of the original representation. Specifically, based on the Extended Gaussian Image (EGI) representation for 3-D models which summarizes the surface normal orientation statistics, we consider these orientations as a random variable, and proceed to search for an optimal transformation for this variable based on genetic optimization. The resulting transformed distribution for the random variable is then used as the modified classifier inputs. Experiments have shown that the optimized transformation results in a significant improvement in classification results for a large variety of class structures. More importantly, the transformation can be indirectly realized by bin removal and bin count merging in the original histogram, thus retaining the advantage of the original EGI representation.

Symmetry detection using complex moments

We present an efficient algorithm for detecting all the symmetry axes of a 2D planar shape. We proved theorems relating to certain distinguishing properties of the generalised complex moments computed for symmetrical objects. Based on these properties, the detection of symmetry axes can be carried out efficiently and accurately. The algorithm can also be applied to detecting partially (perceptually) symmetrical objects.

Similarity measures for histological image retrieval

A gastro-intestinal (GI) tract histological image is usually composed of texture components with different dimensions and properties. To analyze a histological image, we divide it into an array of sub-images. A feature vector comprising a set of Gabor filters and the intensity statistics is computed in order to classify each sub-image to one of 63 histological labels. To retrieve an image from the database, we compare three similarity measures, shape, neighbour and sub-image frequency distribution. It is found that both neighbour and sub-image frequency distribution similarity measures perform similarly well but the shape similarity measure yields the worst result when retrieving images of different GI tract organs. In general, the sub-image frequency distribution measure is the best choice because it requires less time to compute than the neighbour measure.

An Iconic and Semantic Content-Based Retrieval System for Histological Images

This paper describes an intelligent image retrieval system based on iconic and semantic content of histological images. The system first divides an image into a set of subimages. Then the iconic features are derived from primitive features of color histogram, texture and second order statistics of the subimages. These features are then passed to a high level semantic reasoning engine, which generates hypotheses and requests a number of specific fine feature detectors for verification. After iterating a certain number of cycles, a final histological label map is decided for the submitted image. The system may then retrieve images based on either iconic or semantic content. Annotation is also generated for each image processed.

Image retrieval in digital library based on symmetry detection

We present a technique of content-based image retrieval based on the symmetric property of an image and its generalized complex moments. We propose a novel symmetry detection algorithm that is both fast and general compared with existing symmetry detection algorithms. Given the sensitivity of human perception to symmetry, the use of symmetry class helps to ensure that the retrieved images are visually similar. Experimental results show that these features are effective in retrieving binary images and our similarity function is able to rank them first place for nearly all the sample queries used in our experiment.

An object-oriented framework for content-based image retrieval based on 5-tier architecture

Reports a generic object-oriented framework for content-based image retrieval (CBIR) systems. It is designed so that the basic data structures and functionality of a typical CBIR system are provided without sacrificing speed and flexibility. The framework is based on a five-tier architecture that allows modules in different tiers to be developed independently, and thus flexibility is ensured. We show that our framework is able to adapt to a wide range of CBIR applications by applying the framework to the development of two on-going projects: a trademark image retrieval system and a medical (histological) image retrieval system. These applications are briefly discussed.