Baogang Wei

Developing structural constraints for accurate registration of overlapping range images

Automatic image registration is an attractive and unresolved problem in the machine vision literature. This paper presents two novel structural constraints, namely proximity and closeness constraints, that improve both the accuracy and robustness of an existing motion consistency based algorithm (GICP) for automatic image registration. It also defines the conditions when such constraints are fired at specific points of the registration of two overlapping range images. The proximity constraint says that neighbouring points should be neighbouring before and after a rigid motion. The closeness constraint implements a local closest point search from the second image to the first image. While the GICP algorithm uses an exhaustive search for the closest points, in this paper, we employ the optimised k–d tree data structure to accelerate the closest point search. A large number of experiments based on real range images demonstrate that the combination of rigid motion constraints with these novel proximity and closeness constraints leads to a more accurate and robust evaluation of possible correspondences leading, in turn, to more accurate, robust and efficient automatic image registration results.

3D shape matching using collinearity constraint

In this paper, a novel algorithm is proposed to carry out automatic 3D shape matching with 3D shapes represented as sets of points. After the possible matches between the 3D shapes have been determined by the tradition ICP criterion, the novel approach employs the collinearity constraint to eliminate false matches based on a statistical model. A comparative study based on real range images has shown that the proposed algorithm is accurate, robust and efficient for the automatic matching of overlapping 3D shapes.

Using hybrid knowledge engineering and image processing in color virtual restoration of ancient murals

This paper proposes a novel scheme to virtually restore the colors of ancient murals. Our approach integrates artificial intelligence techniques with digital image processing methods. The knowledge related to the mural colors is first categorized into four types. A hybrid frame and rule-based approach is then developed to represent knowledge and to inter colors. An algorithm that takes into account color similarity and spatial proximity is developed to segment mural images. A novel color transformation method based on color histograms is finally proposed to restore the colors of murals. A number of experiments based on real images have demonstrated the validity of the proposed scheme for color restoration.

Discovering treatment pattern in Traditional Chinese Medicine clinical cases by exploiting supervised topic model and domain knowledge

In Traditional Chinese Medicine (TCM), the prescription is the crystallization of clinical experience of doctors, which is the main way to cure diseases in China for thousands of years. Clinical cases, on the other hand, describe how doctors diagnose and prescribe. In this paper, we propose a framework which mines treatment patterns in TCM clinical cases by exploiting supervised topic model and TCM domain knowledge. The framework can reflect principle rules in TCM and improve function prediction of a new prescription. We evaluate our method on 3090 real world TCM clinical cases. The experiment validates the effectiveness of our method.

A GPU-accelerated non-negative sparse latent semantic analysis algorithm for social tagging data

Nowadays large-scale social tagging data have become very valuable in organizing and indexing multimedia resources. In this paper, we apply Non-negative Sparse Latent Semantic Analysis (NN-Sparse LSA) to discover the latent semantic space behind associations between multimedia resources and tagging data. Based on the traditional coordinate-descent algorithm, column-orthogonality and non-negative constraints, we derive a much faster optimization algorithm in theory for solving the NN-Sparse LSA model. Furthermore, we implement the parallel version of our fast NN-Sparse LSA algorithm using the NVIDIA CUDA (Compute Unified Device Architecture) parallel programming framework and a data partitioning scheme that effectively reduces the memory traffic between the global memory of the Graphic Processing Unit (GPU) and the host memory. The experimental results on image classification and tag recommendation tasks on MIRFLICKR and NUS-WIDE datasets show that our parallelized fast optimization algorithm can achieve comparable or even better performance than the other examined methods, while speeds up the original optimization algorithm 20-110 times.

A method for text line detection in natural images

Text information in natural images is very important to cross-media retrieval, index and understanding. However, its detection is challenging due to varying backgrounds, low contrast between text and non-text regions, perspective distortion and other disturbing factors. In this paper, we propose a novel text line detection method which can detect text line aligned with a straight line in any direction. It is mainly composed of three steps. In the first step, we use the maximal stable extremal region detector with dam line constraint to detect candidate text regions, we then define a similarity measurement between two regions which combines sizes, absolute distance, relative distance, contextual information and color histograms. In the second step, we propose a text line identification algorithm based on the defined similarity measurement. The algorithm firstly searches three regions as the seeds of a line, and then expands to obtain all regions in the line. In the last step, we develop a filter to remove non-text lines. The filter uses a sparse classifier based on two dictionaries which are learned from feature vectors extracted from morphological skeletons of those candidate text lines. A comparative study using two datasets shows the excellent performance of the proposed method for accurate text line detection with horizontal or arbitrary consistent orientation.

Regularization Based Iterative Point Match Weighting for Accurate Rigid Transformation Estimation

Feature extraction and matching (FEM) for 3D shapes finds numerous applications in computer graphics and vision for object modeling, retrieval, morphing, and recognition. However, unavoidable incorrect matches lead to inaccurate estimation of the transformation relating different datasets. Inspired by AdaBoost, this paper proposes a novel iterative re-weighting method to tackle the challenging problem of evaluating point matches established by typical FEM methods. Weights are used to indicate the degree of belief that each point match is correct. Our method has three key steps: (i) estimation of the underlying transformation using weighted least squares, (ii) penalty parameter estimation via minimization of the weighted variance of the matching errors, and (iii) weight re-estimation taking into account both matching errors and information learnt in previous iterations. A comparative study, based on real shapes captured by two laser scanners, shows that the proposed method outperforms four other state-of-the-art methods in terms of evaluating point matches between overlapping shapes established by two typical FEM methods, resulting in more accurate estimates of the underlying transformation. This improved transformation can be used to better initialize the iterative closest point algorithm and its variants, making 3D shape registration more likely to succeed.

Efficient shape matching for Chinese calligraphic character retrieval

An efficient search method is desired for calligraphic characters due to the explosive growth of calligraphy works in digital libraries. However, traditional optical character recognition (OCR) and handwritten character recognition (HCR) technologies are not suitable for calligraphic character retrieval. In this paper, a novel shape descriptor called SC-HoG is proposed by integrating global and local features for more discriminability, where a gradient descent algorithm is used to learn the optimal combining parameter. Then two efficient methods, keypoint-based method and locality sensitive hashing (LSH) based method, are proposed to accelerate the retrieval by reducing the feature set and converting the feature set to a feature vector. Finally, a re-ranking method is described for practicability. The approach filters query-dissimilar characters using the LSH-based method to obtain candidates first, and then re-ranks the candidates using the keypoint- or sample-based method. Experimental results demonstrate that our approaches are effective and efficient for calligraphic character retrieval.

Topic Discovery based on LDA_col Model and Topic Significance Re-ranking

This paper presents a method to find the topics efficiently by the combination of topic discovery and topic re-ranking. Most topic models rely on the bag-of-words(BOW) assumption. Our approach allows an extension of LDA model—Latent Dirichlet Allocation_Collocation (LDA_col) to work in corpus such that the word order can be taken into consideration for phrase discovery, and slightly modify the modal for modal consistency and effectiveness. However, LDA_col results may not be ideal for user’s understanding. In order to improve the topic modeling results, two topic significance re-ranking methods (Topic Coverage(TC) and Topic Similarity(TS)) are proposed. We conduct our method on both English and Chinese corpus, the experimental results show that themodified LDA_col discovers more meaningful phrases and more understandable topics than LDA and LDA_col.Meanwhile, topic re-ranking method based on TC performs better than TS, and has the ability of re-ranking the “significant” topics higher than “insignificant” ones.

Projecting registration error for accurate registration of overlapping range images

Abstract In this paper, we propose a novel algorithm for the automatic registration of two overlapping range images. Since it is relatively difficult to compare the registration errors of different point matches, we project them onto a virtual image plane for more accurate comparison using the classical pin-hole perspective projection camera model. While the traditional ICP algorithm is more interested in the points in the second image close to the sphere centred at the transformed point, the novel algorithm is more interested in the points in the second image as collinear as possible to the transformed point. The novel algorithm then extracts useful information from both the registration error and projected error histograms for the elimination of false matches without any feature extraction, image segmentation or the requirement of motion estimation from outliers corrupted data and, thus, has an advantage of easy implementation. A comparative study based on real images captured under typical imaging conditions has shown that the novel algorithm produces good registration results.