Abstract
Shape classification and matching is an important branch of computer vision. It is widely used in image retrieval and target tracking. Shape context method, curvature scale space (CSS) operator and its improvement have been the main algorithms of shape matching and classification. The shape classification network (SCN) algorithm is proposed inspired by LeNet5 basic network structure. Then, the network structure of SCN is introduced and analyzed in detail, and the specific parameters of the network structure are explained. In the experimental part, SCN is used to perform classification tasks on three shape datasets, and the advantages and limitations of our algorithm are analyzed in detail according to the experimental results. SCN performs better than many traditional shape classification algorithms. Accordingly, a practical example is given to show that SCN can save computing resources.
Highlights
Shape classification and matching are an important branch of computer vision
Fourier descriptor based on multiscale centroid contour distance (FMSCCD) [19] is a frequency domain descriptor based on the centroid contour distance (CCD) method, multiscale description, and Fourier transform
The main idea of the traditional shape classification algorithm is to classify based on the proposed descriptor, but the various shapes included in the Animals dataset range from simple to complex, with varying degrees of complexity
Summary
Shape classification and matching are an important branch of computer vision. In recent years, the research on shape classification is still very popular and has made significant results. This kind of representation method has no basic features such as color and texture, it does not affect people to distinguish their species by relying on the eyes and brain. Performing the binary representation of object shapes in the image to obtain shape features; Calculating the similarity between two or more shapes according to certain measurement criteria; Matching and classifying shapes according to calculation results and premise tasks. Through studying some methods of shape matching classification [4,5,6,7,8], it was found that the convolutional neural network shows good results in object detection [9].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
