Extraction of affine invariant features for shape recognition based on ant colony optimization

A new approach to extraction of affine invariant features of contour image and matching strategy is proposed for shape recognition.Firstly,the centroid distance and azimuth angle of each boundary point are computed.Then,with a prior-defined angle interval,all the points in the neighbor region of the sample point are considered to calculate the average distance for eliminating noise.After that,the centroid distance ratios（CDRs） of any two opposite contour points to the barycenter are achieved as the representation of the shape,which will be invariant to affine transformation.Since the angles of contour points will change non-linearly among affine related images,the CDRs should be resampled and combined sequentially to build one-by-one matching pairs of the corresponding points.The core issue is how to determine the angle positions for sampling,which can be regarded as an optimization problem of path planning.An ant colony optimization（ACO）-based path planning model with some constraints is presented to address this problem.Finally,the Euclidean distance is adopted to evaluate the similarity of shape features in different images.The experimental results demonstrate the efficiency of the proposed method in shape recognition with translation,scaling,rotation and distortion.

Composite Distance Transformation for Indexing and κ-Nearest-Neighbor Searching in High-Dimensional Spaces

Due to the famous dimensionality curse problem, search in a high-dimensional space is considered as a ＂hard＂ problem. In this paper, a novel composite distance transformation method, which is called CDT, is proposed to support a fast κ-nearest-neighbor （κ-NN） search in high-dimensional spaces. In CDT, all （n） data points are first grouped into some clusters by a κ-Means clustering algorithm. Then a composite distance key of each data point is computed. Finally, these index keys of such n data points are inserted by a partition-based B^＋-tree. Thus, given a query point, its κ-NN search in high-dimensional spaces is transformed into the search in the single dimensional space with the aid of CDT index. Extensive performance studies are conducted to evaluate the effectiveness and efficiency of the proposed scheme. Our results show that this method outperforms the state-of-the-art high-dimensional search techniques, such as the X-Tree, VA-file, iDistance and NB-Tree.

Grading method for tomato multi-view shape using machine vision

Owing to the requirements of a high yield and high-quality tomatoes, tomato grading is important-particularly for fruit morphology, and accuracy has become the focus of attention. Machine vision provides a fast and nondestructive manner to address this demand. In this study, the gamma correction method was used for preprocessing to enhance the edge information of tomatoes, and Otsu’s method was used to eliminate the tomato-image background in the A-component image under the LAB color model. On this basis, two levels of exploration were conducted. First, new evaluation indices were proposed for tomato shapes from different views. For the top view, two shape-evaluation indices were established: the area ratio of the maximum inscribed circle to the maximum circumscribed circle and the dispersion of the contour centroid distance (range and coefficient of variation), the highest accuracy was 94%. For the side view, the difference between the maximum and minimum centroid distances in the contour was established as a shape index, the highest accuracy was 91.91%. Second, an evaluation method based on multi-view fusion was developed by combining the advantage indices for different views. The classification accuracy reached 96%, with the highest identification accuracy of unqualified tomatoes. The results show that the proposed evaluation method combining top views (dispersion of centroid distance) with side views (difference between maximum and minimum centroid distances) is effective for classifying tomatoes.