Object restoration based on extrinsic reflective symmetry plane detection

Xu, Jianwen; Cao, Wei; Liu, Bin; Jiang, Kaiyong

doi:10.1007/s00371-021-02192-5

Cited by 4 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Detecting regular and symmetry shapes is essential in computer vision and pattern recognition communities. Regular and symmetry shape detection are broadly used in urban scene recognition [3,4,23], vehicle recognition [5,6], face analysis [7,8], image reconstruction [9], and driver assistance systems [10]. Moreover, the regular and symmetry shape features are considered salient features that guide eye movements and can thus mainly be used for visual attention detection [11].…”

Section: Introductionmentioning

confidence: 99%

A Novel Hierarchical Shape Analysis based on Sampling Point-Line Distance for Regular and Symmetry Shape Detection

Xian¹

2022

IJACSA

View full text Add to dashboard Cite

Regular and symmetry shapes occurred in natural and manufactured objects. Detecting these shapes are essential and still tricky task in computer vision. This paper proposes a novel hierarchical shape detection (HiSD) method, which consists of circularity and roundness detection, and regularity and symmetry detection phases. The first phase recognizes the circular and elliptical shapes using aspect ratio and roundness measurements. The second phase, the main phase in the HiSD, recognizes the regular and symmetry shapes using density distribution measurement (DDM) and the proposed sampling point-line distance distribution (SPLDD) algorithm. The proposed method presets effective with low computation cost shape detection approach which is not sensitive to specific category of objects. It enables to detect different types of objects involving the arbitrary, regular, and symmetry shapes. Experimental results show that the proposed method performs well compared to the existing state-of-the-art algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Hierarchical Shape Analysis based on Sampling Point-Line Distance for Regular and Symmetry Shape Detection

Xian¹

2022

IJACSA

View full text Add to dashboard Cite

show abstract

Efficient feature fusion network based on center and scale prediction for pedestrian detection

et al. 2022

View full text Add to dashboard Cite

Digital design and evaluation for additive manufacturing of personalized myopic glasses

Liu

Wang

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Myopic glasses design has critical effects on the match between glasses and individual face. Improper myopic glasses design may affect the try-on comfort and health. It is difficult for the myopic glasses to be adjusted variedly and suitably from people to people with the limitations of traditional manufacturing processes and current design methods. In this paper, an evaluation descriptor named glasses fit score, which contains alignment scores and design scores, is proposed to guide and evaluate the myopic glasses design. Based on the descriptor, a novel approach is presented to complete the myopic glasses design and manufacturing individually. The approach can be divided into three steps: glasses alignment, glasses personalized design and glasses manufacturing. During the glasses alignment, the myopic glasses are aligned to the face to obtain the alignment score of the descriptor based on the face symmetry plane and feature points, including the silent point of the eye and the top point of the ear. After the glasses alignment, the myopic glasses can be deformed to match the face to achieve the design score of the descriptor. The deformations include glasses frame transformation, glasses leg option and glasses personalized mark. In the glasses manufacturing, the designed myopic glasses can be fabricated by a 3D printer. Then, a post processing process is conducted to polish the myopic glasses with oil painted. Finally, the proposed approach is applied to adjust the myopic glasses for several people. The results show that, compared to the previous methods, the approach can make the myopic glasses aligned and deformed to the individual face effectively to obtain an ideal score of the descriptor, thus improving the match between the glasses and the individual face.

show abstract

Object restoration based on extrinsic reflective symmetry plane detection

Cited by 4 publications

References 43 publications

A Novel Hierarchical Shape Analysis based on Sampling Point-Line Distance for Regular and Symmetry Shape Detection

A Novel Hierarchical Shape Analysis based on Sampling Point-Line Distance for Regular and Symmetry Shape Detection

Efficient feature fusion network based on center and scale prediction for pedestrian detection

Digital design and evaluation for additive manufacturing of personalized myopic glasses

Contact Info

Product

Resources

About