Advanced feature point transformation of corner points for mobile object recognition

Xiyuan, Yin; Kim, Dae-Hwan; Hong, Chung-Pyo; Kim, Cheong-Ghil; Kim, Kuinam J.; Kim, Shin-Dug

doi:10.1007/s11042-014-2241-6

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Any pattern, which has a great dissimilarity over its neighbor patterns, is defined as an SDPF. The dissimilarity of two dither patterns is specified as in (4).…”

Section: Salient Dither Pattern Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Nature Inspired Dimensional Reduction Technique for Fast and Invariant Visual Feature Extraction

Bandara

Ranathunga

Abdullah

2019

IJATCSE

View full text Add to dashboard Cite

Fast and invariant feature extraction is crucial in certain computer vision applications where the computation time is constrained in both training and testing phases of the classifier. In this paper, we propose a nature-inspired dimensionality reduction technique for fast and invariant visual feature extraction. The human brain can exchange the spatial and spectral resolution to reconstruct missing colors in visual perception. The phenomenon is widely used in the printing industry to reduce the number of colors used to print, through a technique, called color dithering. In this work, we adopt a fast error-diffusion color dithering algorithm to reduce the spectral resolution and extract salient features by employing novel Hessian matrix analysis technique, which is then described by a spatial-chromatic histogram. The computation time, descriptor dimensionality and classification performance of the proposed feature are assessed under drastic variances in orientation, viewing angle and illumination of objects comparing with several different state-of-the-art handcrafted and deep-learned features. Extensive experiments on two publicly available object datasets, coil-100 and ALOI carried on both a desktop PC and a Raspberry Pi device show multiple advantages of using the proposed approach, such as the lower computation time, high robustness, and comparable classification accuracy under weakly supervised environment. Further, it showed the capability of operating solely inside a conventional SoC device utilizing a small fraction of the available hardware resources.

show abstract

“…Any pattern, which has a great dissimilarity over its neighbor patterns, is defined as an SDPF. The dissimilarity of two dither patterns is specified as in (4).…”

Section: Salient Dither Pattern Feature Extractionmentioning

confidence: 99%

“…In addition to the computational cost, the state-of-the-art machine learned features are less invariant to dramatic geometrical transformation and illumination. Hence, generic handcrafted features can be more suitable for some applications which require invariant performance, faster execution with better adaptability [4,5].…”

Section: Introductionmentioning

confidence: 99%

Nature Inspired Dimensional Reduction Technique for Fast and Invariant Visual Feature Extraction

Bandara

Ranathunga

Abdullah

2019

IJATCSE

View full text Add to dashboard Cite

show abstract

Video Stabilization Algorithm Based on Kalman Filter and Homography Transformation

Liu

2017

Advances in Internetworking, Data &Amp; Web Technologies

View full text Add to dashboard Cite

Robust global motion estimation for video security based on improved k-means clustering

Liu

et al. 2018

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Advanced feature point transformation of corner points for mobile object recognition

Cited by 3 publications

References 12 publications

Nature Inspired Dimensional Reduction Technique for Fast and Invariant Visual Feature Extraction

Nature Inspired Dimensional Reduction Technique for Fast and Invariant Visual Feature Extraction

Video Stabilization Algorithm Based on Kalman Filter and Homography Transformation

Robust global motion estimation for video security based on improved k-means clustering

Contact Info

Product

Resources

About