Director Field Model of the Primary Visual Cortex for Contour Detection
원문 초록
We aim to build the simplest possible model capable of detecting long, noisy contours in a cluttered visual scene. For this, we model the neural dynamics in the primate primary visual cortex in terms of a continuous director field that describes the average rate and the average orientational preference of active neurons at a particular point in the cortex. We then use a linear-nonlinear dynamical model with long range connectivity patterns to enforce long-range statistical context present in the analyzed images. The resulting model has substantially fewer degrees of freedom than traditional models, and yet it can distinguish large contiguous objects from the background clutter by suppressing the clutter and by filling-in occluded elements of object contours. This results in high-precision, high-recall detection of large objects in cluttered scenes. Parenthetically, our model has a direct correspondence with the Landau - de Gennes theory of nematic liquid crystal in two dimensions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
KnotResolver: Tracking self-intersecting filaments in microscopy using directed graphs
AutArch: An AI-assisted workflow for object detection and automated recording in archaeological catalogues
Tiny and Efficient Model for the Edge Detection Generalization
$CrowdDiff$: Multi-hypothesis Crowd Density Estimation using Diffusion Models
Segmentation of Blood Vessels, Optic Disc Localization, Detection of Exudates and Diabetic Retinopathy Diagnosis from Digital Fundus Images
Hardware-accelerated Mars Sample Localization via deep transfer learning from photorealistic simulations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.