Rongchun Zhao

Morphology-based multifractal estimation for texture segmentation

Multifractal analysis is becoming more and more popular in image segmentation community, in which the box-counting based multifractal dimension estimations are most commonly used. However, in spite of its computational efficiency, the regular partition scheme used by various box-counting methods intrinsically produces less accurate results. In this paper, a novel multifractal estimation algorithm based on mathematical morphology is proposed and a set of new multifractal descriptors, namely the local morphological multifractal exponents is defined to characterize the local scaling properties of textures. A series of cubic structure elements and an iterative dilation scheme are utilized so that the computational complexity of the morphological operations can be tremendously reduced. Both the proposed algorithm and the box-counting based methods have been applied to the segmentation of texture mosaics and real images. The comparison results demonstrate that the morphological multifractal estimation can differentiate texture images more effectively and provide more robust segmentations.

Image segmentation by clustering of spatial patterns

This letter describes an approach to perceptual segmentation of images through the means of clustering of spatial patterns. An image is modeled as a set of spatial patterns defined on a rectangular lattice. The distance between a spatial pattern and each cluster is defined as a combination of the Euclidean distance in the feature space and the spatial dissimilarity which reflects how much of the patterns neighbourhood is occupied by other clusters. Our approach has been compared with the Fuzzy C-Mean (FCM) algorithm, a spatial fuzzy clustering algorithm and a Markov Random Field (MRF) based algorithm by segmenting synthetic images, texture mosaics and natural images. The results of those comparative experiments demonstrate that the proposed approach can segment images more effectively and provide more robust segmentation results.

Hierarchical content classification and script determination for automatic document image processing

Page segmentation and image content classification plays an important role in automatic document image processing with applications to mixed-type document image compression, form and check reading, and automatic mail sorting. We propose an enhanced background-thinning based page segmentation algorithm to process document images rapidly and eliminate some small regions embedded in other regions. We then present a hierarchical approach, which combines the cross correlation measure, Kolmogorov complexity measure, and a neural network, to classify sub-images into halftones and texts. The approach also achieves high accuracy in text determination using a three-layer feed-forward network where the text region can be classified into Chinese or alphabetic characters. Experimental results on a number of mixed-type document images show the efficiency and effectiveness of our approach.

Robust shape-based head tracking

This work presents a new method to automatically locate frontal facial feature points under large scene variations (illumination, pose and facial expressions). First, we use a kernel-based tracker to detect and track the facial region in an image sequence. Then the results of the face tracking, i.e. face region and face pose, are used to constrain prominent facial feature detection and tracking. In our case, eyes and mouth corners are considered as prominent facial features. In a final step, we propose an improvement to the Bayesian Tangent Shape Model for the detection and tracking of the full shape model. A constrained regularization algorithm is proposed using the head pose and the accurately aligned prominent features to constrain the deformation parameters of the shape model. Extensive experiments demonstrate the accuracy and effectiveness of our proposed method.

The immune quantum-inspired evolutionary algorithm

By leading immune concepts and methods into quantum-inspired evolutionary algorithm (QEA), a novel algorithm, the immune quantum-inspired evolutionary algorithm (IQEA), is proposed. On condition of preserving QEAs advantages, IQEA utilizes some characteristics and knowledge in the pending problems for restraining the repeat and ineffective operations during evolution, so as to improve the algorithm efficiency. The experimental results of the knapsack problem show that the performance of IQEA is superior to the conventional EA (CEA), the immune EA (IEA) and QEA.

A new method for edge detection

A hybrid genetic quantum algorithm (GQA) is proposed for edge detection. GQA is based on the concept and principles of quantum computing such as qubits and superposition of states. By adopting qubit chromosome, GQA can represent a linear superposition of solutions due to its probabilistic representation. Thus, GQA has a better characteristic of diversity and better global search capability than classical approaches. We combine GQA and the local search technique to the problem of edge detection. Experiment results show that the algorithm perform well in terms of quality of the final edge image, rate of convergence and robustness to noise.

Multi-stream Asynchrony Modeling for Audio-Visual Speech Recognition

In this paper, two multi-stream asynchrony Dynamic Bayesian Network models (MS-ADBN model and MM-ADBN model) are proposed for audio-visual speech recognition (AVSR). The proposed models, with different topology structures, loose the asynchrony of audio and visual streams to word level. For MS-ADBN model, both in audio stream and in visual stream, each word is composed of its corresponding phones, and each phone is associated with observation vector. MM- ADBN model is an augmentation of MS-ADBN model, a level of hidden nodes--state level, is added between the phone level and the observation node level, to describe the dynamic process of phones. Essentially, MS-ADBN model is a word model, while MM-ADBN model is a phone model. Speech recognition experiments are done on a digit audio-visual (A-V) database, as well as on a continuous A-V database. The results demonstrate that the asynchrony description between audio and visual stream is important for AVSR system, and MM-ADBN model has the best performance for the task of continuous A-V speech recognition.

A novel immune quantum-inspired genetic algorithm

A new algorithm, the immune quantum-inspired genetic algorithm (IQGA), is proposed by introducing immune concepts and methods into quantum-inspired genetic algorithm (QGA). In application to the knapsack problem, which is a well-known combinatorial optimization problem, the proposed algorithm performs better than the conventional GA (CGA), the immune GA (IGA) and QGA.

Hidden Markov random field based approach for off-line handwritten Chinese character recognition

This paper presents a hidden Markov mesh random field (HMMRF) based approach for off-line handwritten Chinese characters recognition using statistical observation sequences embedded in the strokes of a character. Due to a large set of Chinese characters and many different writing styles, the recognition of handwritten Chinese characters is very challenging. In our approach, the binary image is first normalized by a nonlinear shape normalization scheme to adjust the width, length, and the correlation of strokes. Two types of stroke-based features are then extracted to represent the observation sequence. The estimation of model parameters and state sequence decoding algorithms are also discussed in the paper. Experimental results on 470 isolated handwritten Chinese characters demonstrate the effectiveness of our approach.

Multifractal signature estimation for textured image segmentation

Fractal theory provides a powerful mathematical tool for texture segmentation. However, in spite of their increasing popularity, traditional fractal features are intrinsically of less accuracy due to the difference between the idea fractal model and the fractal reality of digital images. In this paper, we incorporated the multifractal analysis method into the idea of fractal signature, and thus proposed a novel type of texture descriptor called multifractal signature, which characterizes the variation of multifractal dimensions over spatial scales. In our approach, the local multifractal dimension of each scale was calculated by using the measurement acquired at two successive scales so that the time-consuming and less accurate least square fit was avoided. Based on three popular multifractal measurements, the differential box-counting (DBC) based multifractal signature, relative DBC based multifractal signature, and morphological multifractal signature were presented in this paper. The performance of the proposed texture descriptors was evaluated for segmentation of texture mosaics by comparing to the corresponding multifractal dimensions. The experimental results demonstrated that multifractal signatures can differentiate textured images more effectively and provide more robust segmentations.