no code implementations • 17 Apr 2024 • Hanlin Mo, Guoying Zhao
Based on various types of non-learnable operators, including gradient, sort, local binary pattern, maximum, etc., this paper designs a set of new convolution operations that are natually invariant to arbitrary rotations.
no code implementations • 23 May 2023 • Hanlin Mo, Guoying Zhao
The topic of achieving rotational invariance in convolutional neural networks (CNNs) has gained considerable attention recently, as this invariance is crucial for many computer vision tasks such as image classification and matching.
no code implementations • 25 Mar 2023 • Hanlin Mo, Hongxiang Hao, Guoying Zhao
Further, we achieve their invariance to similarity transform.
no code implementations • 21 Nov 2022 • Hanlin Mo, Guoying Zhao
Using MNIST dataset, we first evaluate the rotation invariance of RIC-CNN and compare its performance with most of existing rotation-invariant CNN models.
no code implementations • 3 Jan 2022 • Hanlin Mo, Hua Li, Guoying Zhao
Then, we design a structural framework to generate Gaussian-Hermite moment invariants for these two transform models systematically.
no code implementations • 21 Apr 2020 • Qi Li, Hanlin Mo, Jinghan Zhao, Hongxiang Hao, Hua Li
The dynamics of human skeletons have significant information for the task of action recognition.
no code implementations • 19 Nov 2019 • You Hao, Hanlin Mo, Qi Li, He Zhang, Hua Li
In this paper, we propose a general framework to derive moment invariants under DAT for objects in M-dimensional space with N channels, which can be called dual-affine moment invariants (DAMI).
no code implementations • 13 Nov 2019 • Hanlin Mo, Hua Li
As far as we know, no previous papers have published so many explicit forms of high-order rotation differential invariants of images.
no code implementations • 30 Aug 2018 • He Zhang, Hanlin Mo, You Hao, Qi Li, Hua Li
According to the Liouville Theorem, an important part of the conformal transformation is the Mobius transformation, so we focus on Mobius transformation and propose two differential expressions that are invariable under 2-D and 3-D Mobius transformation respectively.
no code implementations • 20 Oct 2017 • He Zhang, Hanlin Mo, You Hao, Shirui Li, Hua Li
And the five chiral invariants have four characteristics:(1) They play an important role in the detection of symmetry, especially in the treatment of 'false zero' problem.
no code implementations • 19 Jul 2017 • Erbo Li, Hanlin Mo, Dong Xu, Hua Li
In this paper, we propose relative projective differential invariants (RPDIs) which are invariant to general projective transformations.
no code implementations • 14 Jun 2017 • Hanlin Mo, Shirui Li, You Hao, Hua Li
We propose the general construction formula of shape-color primitives by using partial differentials of each color channel in this paper.
no code implementations • 5 Jun 2017 • Hanlin Mo, You Hao, Shirui Li, Hua Li
A new kind of geometric invariants is proposed in this paper, which is called affine weighted moment invariant (AWMI).
no code implementations • 31 May 2017 • Ming Gong, You Hao, Hanlin Mo, Hua Li
We proposed a kind of naturally combined shape-color affine moment invariants (SCAMI), which consider both shape and color affine transformations simultaneously in one single system.
no code implementations • 19 May 2017 • You Hao, Shirui Li, Hanlin Mo, Hua Li
We present a novel Affine-Gradient based Local Binary Pattern (AGLBP) descriptor for texture classification.