A two-stage text detection approach using gradient point adjacency and deep network
1
Citation
0
Reference
10
Related Paper
Citation Trend
Abstract:
Scene text detection is a pivotal problem in computer vision and image processing research. In this paper, a fair attempt is made to design a simple yet effective text detection method in Indic script environment. At first, a fine-scale edge-map is generated from the original image, and subsequently, adaptive clustering is applied to form clusters of edge-points based on their spatial density. Foreground objects are extracted with the help of cluster boundaries and considered as prospective text proposals. Such text proposals are fed to a deep convolutional neural network for learning and prediction as text and non-texts. Finally, true-text components are aggregated as localised final texts of the original image. The proposed method is evaluated on two benchmark datasets viz. ICDAR 2017-MLT and ICDAR 2013 born image, and obtained results are found to surpass some other state-of-the-art methods, which demonstrates its effectiveness in scene and digital environments.Keywords:
Benchmark (surveying)
Adjacency list
Text Detection
This article presents a new construction algorithm for computer – aided plant layout. A case study is an assembly plant which will be expanded to construct a new plant. The layouts are generated by ALDEP and Adjacency – Based Heuristic that are evaluated by the maximize adjacency – based objective. The solution will be developed on the basis of mathematical expressions that can be evaluated objectively. For the results, found that the layout generated from Adjacency – Based Heuristic has the layout score better than the layout is generated by ALDEP, and Adjacency – Based Heuristic can generate the material handling distance less than the layout is generated by ALDEP.
Adjacency list
Page layout
Adjacency matrix
Cite
Citations (0)
Edge detection has a very important application in image processing and computer vision.This paper introduced and analyzed several typical methods of edge detection in digital image processing,at the same time,compares each method and indicates the advantages and disadvantages of each method through VC++ experience,provide the comparison and the reference for uses which algorithm to the practical application.
Cite
Citations (5)
Abstract A new data structure, called the Edge‐Oriented Adjacency List (EOAL), for representing undirected graphs is presented. It provides more information on the edges and requires less storage space than the conventional adjacency list. Furthermore, it is superior to the conventional adjacency list in both insertion and deletion operations.
Adjacency list
Undirected graph
Adjacency matrix
Cite
Citations (1)
Adjacency list
Adjacency matrix
Cite
Citations (31)
Adjacency list
Floor plan
Adjacency matrix
Cite
Citations (6)
Edge-detection is all the time a major problem in the computer early vision, and it plays an important role in image processing. This paper reviews classical and new methods of edge-detection and discusses its application in medical image processing.
Image edge
Cite
Citations (6)
Real time object detection in traffic surveillance is one of the latest topics in today's world using Region based Convolutional Neural Networks algorithm in comparison with Convolutional Neural Networks. Real-Time Object Detection is performed using Regional Convolutional Neural Networks (N=78) over Convolutional Neural Networks (N=78) with the split size of training and testing dataset 70% and 30% respectively. Regional Convolutional Neural Networks had significantly better accuracy (75.6%) compared to Convolutional Neural Networks (47.7%) and attained significance value of p=0.041. Regional Convolutional Neural Networks achieved significantly better object detection than Convolutional Neural Networks for identifying real-time objects in traffic surveillance.
Cite
Citations (8)
Adjacency list
Adjacency matrix
Graph energy
Cite
Citations (11)
Adjacency list
Floor plan
Breadth-first search
Tree (set theory)
Cite
Citations (30)
A method is presented for determining whether two given regions are adjacent, and for finding all the neighbors of different sizes for a given region. Regions are defined as elementary squares of any size. In a companion paper [ 2 ], we introduce the quadcode and discuss its use in representing geometric concepts in the coded image, such as location, distance, and adjacency. In this paper we give a further discussion of adjacency in terms of quadcodes. Gargantini [ 1 ] discussed adjacency detection using linear quadtrees. Her discussion was applied to pixels, and a procedure was given to find a pixel's southern neighbor only. This paper considers elementary squares of any size, and gives procedures for both aspects of the problem: for determining whether two given regions are adjacent, and for finding all the neighbors of different sizes for a given region.
Adjacency list
Adjacency matrix
Least-squares function approximation
Cite
Citations (25)