Search Results for author: Azeddine Beghdadi

Found 8 papers, 3 papers with code

A New Lightweight Hybrid Graph Convolutional Neural Network -- CNN Scheme for Scene Classification using Object Detection Inference

1 code implementation19 Jul 2024 Ayman Beghdadi, Azeddine Beghdadi, Mohib Ullah, Faouzi Alaya Cheikh, Malik Mallem

Scene understanding plays an important role in several high-level computer vision applications, such as autonomous vehicles, intelligent video surveillance, or robotics.

Autonomous Vehicles object-detection +3

CD-COCO: A Versatile Complex Distorted COCO Database for Scene-Context-Aware Computer Vision

1 code implementation12 Nov 2023 Ayman Beghdadi, Azeddine Beghdadi, Malik Mallem, Lotfi Beji, Faouzi Alaya Cheikh

These new local distortions are generated by considering the scene context of the images that guarantees a high level of photo-realism.

object-detection Object Detection +2

Enhancing road signs segmentation using photometric invariants

no code implementations26 Oct 2020 Tarik Ayaou, Azeddine Beghdadi, Karim Afdel, Abdellah Amghar

Road signs detection and recognition in natural scenes is one of the most important tasksin the design of Intelligent Transport Systems (ITS).

Segmentation

Adaptive Context Encoding Module for Semantic Segmentation

no code implementations13 Jul 2019 Congcong Wang, Faouzi Alaya Cheikh, Azeddine Beghdadi, Ole Jakob Elle

The object sizes in images are diverse, therefore, capturing multiple scale context information is essential for semantic segmentation.

Semantic Segmentation

Can Image Enhancement be Beneficial to Find Smoke Images in Laparoscopic Surgery?

no code implementations27 Dec 2018 Congcong Wang, Vivek Sharma, Yu Fan, Faouzi Alaya Cheikh, Azeddine Beghdadi, Ole Jacob Elle, Rainer Stiefelhagen

For feature extraction, we use statistical features based on bivariate histogram distribution of gradient magnitude~(GM) and Laplacian of Gaussian~(LoG).

General Classification Image Enhancement +1

Cannot find the paper you are looking for? You can Submit a new open access paper.