Papers by Chengzhuan Yang
Metal surface Feature Fusion for Defect Recognition
Composite descriptor based on contour and appearance for plant species identification
Engineering applications of artificial intelligence, Jul 1, 2024
End-to-end point supervised object detection with low-level instance features
Applied soft computing, May 1, 2024
CSPNeXt: A new efficient token hybrid backbone
Engineering Applications of Artificial Intelligence, May 31, 2024
Learning Robust Point Representation for 3D Non-Rigid Shape Retrieval
IEEE Transactions on Multimedia, Dec 31, 2022
Fuzziness based on covering generalized rough sets
The uncertainty measurement of rough sets is one of the key problems in the rough set theory. The... more The uncertainty measurement of rough sets is one of the key problems in the rough set theory. The rough membership function provides a new interpretation for rough sets and serves as an approach for measuring their uncertainty. This paper presents a novel measure of fuzziness based on covering generalized rough sets and its properties. We define the rough membership function for the fourth type of covering generalized rough sets and prove some relevant properties, and then the fuzziness is defined based on the proposed rough membership function. A specific example is illustrated to explain the fuzziness. Last, we put forward a reasonable rough membership function for the fuzziness of irrationality of the third type of covering generalized rough sets.
Uncertainty measures of covering rough sets based on knowledge granularities
This paper has analyzed the existent measures of uncertainty based on covering rough sets. It is ... more This paper has analyzed the existent measures of uncertainty based on covering rough sets. It is revealed that they all bear some irrationality under specified situations. Here a concept of relative knowledge granularities based on covering rough sets is defined. And we propose an uncertainty measure of covering rough sets based on knowledge granularities and prove its relevant properties. Analysis has proven that the uncertainty measuring approach overcomes the irrationality of former approaches, so it provides a new method for measuring the uncertainty of covering rough sets.
Multi-level contour combination features for shape recognition
Computer Vision and Image Understanding, Mar 1, 2023
Shape-based object recognition via Evidence Accumulation Inference
Pattern Recognition Letters, Jul 1, 2016
We proposed a structural representation of shapes using Bayesian Network.We proposed a way of Evi... more We proposed a structural representation of shapes using Bayesian Network.We proposed a way of Evidence Accumulation Inference to pick up region of interest.Our method achieves the state-of-the-art performance on ETHZ shape classes. Shape-based object recognition is one of the most challenging problems in computer vision. Learning a structural representation using graphical models is a new trend in object recognition. This paper tries to apply graphical models to learn a shape representation and proposes a pipeline of shape-based object recognition. First, a Bayesian Network represents the shape knowledge of a type of object. Second, an Evidence Accumulation Inference with Bayesian Network is developed to search for the region of interest which is most likely to contain an object in an image. Finally, a spatial pyramid matching approach is used to verify the hypothesis to identify objects and to refine object locations. Our experiments corroborate that Evidence Accumulation Inference with Bayesian Network for object recognition is correct and show that the proposed pipeline achieves comparable results on well-known ETHZ shape classes and INRIA Horse dataset.
Part-Wise AtlasNet for 3D point cloud reconstruction from a single image
Knowledge Based Systems, Apr 1, 2022
Deep convolutional feature aggregation for fine-grained cultivar recognition
Knowledge-Based Systems
Multi-level contour combination features for shape recognition
Computer Vision and Image Understanding
A Learning Robust and Discriminative Shape Descriptor for Plant Species Identification
IEEE/ACM Transactions on Computational Biology and Bioinformatics
Plant identification based on leaf images is a widely concerned application field in artificial i... more Plant identification based on leaf images is a widely concerned application field in artificial intelligence and botany. The key problem is extracting robust discriminative features from leaf images and assigning a measure of similarity. This study proposes an effective, robust shape descriptor to identify plant species from images of their leaves, which we call the high-level triangle shape descriptor (HTSD). First, we extract a leaf images external contour and internal salient point information. We then use triangle features to describe the leaf contour, which we call the contour point based on triangle features (CPTFs). The internal information of the leaf image is based on salient point triangle features (SPTFs). The third step is to apply the Fisher vector to encode the two kinds of point-based local triangle features into the HTSD. Finally, we employ the simple Euclidean distance to calculate the dissimilarities between the HTSD characteristics of leaf images. We have extensively evaluated the proposed approach on several public leaf datasets successfully. Experimental results show that our method has superior recognition accuracy, outperforming current state-of-the-art shape-based and deep-learning plant identification approaches.
Plant leaf identification based on shape and convolutional features
Expert Systems with Applications
Part-Wise AtlasNet for 3D point cloud reconstruction from a single image
Knowledge-Based Systems, 2022
IEEE Access, 2020
This article proposes a novel contour-based mid-level shape description method for shape classifi... more This article proposes a novel contour-based mid-level shape description method for shape classification. This method resolves the shortcomings of low-level shape descriptors in dealing with the shapes of objects with large intra-class changes and non-linear deformation (articulation, occlusion and noise), thus improving the accuracy of shape classification. First, we extract the outer contour of an object and sample it. We next describe each sampling point on the shape contour with a triangular feature and regard it as a local feature. Then, a shape codebook is learned, and the Fisher vector encoding method is used to produce a compact mid-level shape feature. Finally, the learned mid-level shape features are sent to the linear support vector machine (SVM) classifier for shape recognition. The proposed method has been extensively tested on several standard shape datasets, and the experimental results show that our approach attains high accuracy of shape classification. Comparisons to other state-of-the-art shape classification approaches further prove the superiority and effectiveness of our method. INDEX TERMS Shape classification, triangular feature, fisher vector, mid-level shape representation.
Multiscale Triangular Centroid Distance for Shape-Based Plant Leaf Recognition
Plant leaf recognition by integrating shape and texture features
Pattern Recognition, 2021
Latent-MVCNN: 3D Shape Recognition Using Multiple Views from Pre-defined or Random Viewpoints
Neural Processing Letters, 2020
The Multi-view Convolution Neural Network (MVCNN) has achieved considerable success in 3D shape r... more The Multi-view Convolution Neural Network (MVCNN) has achieved considerable success in 3D shape recognition. However, 3D shape recognition using view-images from random viewpoints has not been yet exploited in depth. In addition, 3D shape recognition using a small number of view-images remains difficult. To tackle these challenges, we developed a novel Multi-view Convolution Neural Network, “Latent-MVCNN” (LMVCNN), that recognizes 3D shapes using multiple view-images from pre-defined or random viewpoints. The LMVCNN consists of three types of sub Convolution Neural Networks. For each view-image, the first type of CNN outputs multiple category probability distributions and the second type of CNN outputs a latent vector to help the first type of CNN choose the decent distribution. The third type of CNN outputs the transition probabilities from the category probability distributions of one view to the category probability distributions of another view, which further helps the LMVCNN to find the decent category probability distributions for each pair of view-images. The three CNNs cooperate with each other to the obtain satisfactory classification scores. Our experimental results show that the LMVCNN achieves competitive performance in 3D shape recognition on ModelNet10 and ModelNet40 for both the pre-defined and the random viewpoints and exhibits promising performance when the number of view-images is quite small.
IEEE Access, 2019
Plant species recognition using leaf images is a highly important and challenging issue in botany... more Plant species recognition using leaf images is a highly important and challenging issue in botany and pattern recognition. A center problem of this task is how to accurately extract leaf image characteristics and quickly calculate the similarity between them. This article presents a new shape description approach called triangle-distance representation (TDR) for plant leaf recognition. The TDR descriptor is represented by two matrices: a sign matrix and a triangle center distance matrix. The sign matrix is used to characterize the convex/concave property of a shape contour, while the triangle center distance matrix is used to represent the bending degree and spatial information of a shape contour. This method can effectively capture the detailed and global characteristics of a leaf shape while keeping the similarity transformations (translation, rotation, and scaling) unchanged. In addition, this method is quite compact and has low computational complexity. We tested our method on four standard plant leaf datasets, including the famous Swedish, Smithsonian, Flavia, and ImageCLEF2012 datasets. The results confirm that our approach exceeds the prior state-of-the-art shape-based plant leaf recognition approaches. An extra experiment on the MPEG-7 shape dataset further shows that our method can be applied to general shape recognition.
Uploads
Papers by Chengzhuan Yang