Security system using mobile image processing and color recognition for the visually impaired
Eugene Rhee,Junhee Cho +1 more
1
TL;DR: This paper proposes the development of an application that can efficiently and independently recognize colors and images at anytime, anywhere by scanning images using smartphone cameras and converting them into bitmap images.
read more
Abstract: Voice technology at traffic lights or bus stops is emerging for the independent daily life of the blind, but there are few technologies that efficiently help the blind, such as knowing the color of clothes to wear before going out or entering the bus stop at once. To support such difficulties, this paper proposes a method that can be helped by using a smartphone application to distinguish the color of outdoor clothes. Smartphones, which are hardware-based for applications, have the advantage of predictable results, ease of transportation, independence from direct use, and personal support for the blind through various applications. However, there are very few applications to help the blind. This paper proposes the development of an application that can efficiently and independently recognize colors and images at anytime, anywhere by scanning images using smartphone cameras and converting them into bitmap images. Finally, the effects that can be expected through the application proposed in this study are described.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Indonesian Journal of Electrical Engineering and Computer Science
TL;DR: In this article , the authors proposed a unified power quality control (UPQC) to mitigate the power quality problems caused by using power electronics devices, which is made by the distributed generation of dynamic voltage restorer (DVR) and static synchronous compensator (STATCOM) with the DC-link.
References
Guided Image Filtering
Kaiming He,Jian Sun,Xiaoou Tang +2 more
TL;DR: The guided filter is a novel explicit image filter derived from a local linear model that can be used as an edge-preserving smoothing operator like the popular bilateral filter, but it has better behaviors near edges.
Learning to Compare: Relation Network for Few-Shot Learning
Flood Sung,Yongxin Yang,Li Zhang,Tao Xiang,Philip H. S. Torr,Timothy M. Hospedales +5 more
- 18 Jun 2018
TL;DR: A conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each, which is easily extended to zero- shot learning.
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
Hongyang Li,David Eigen,Samuel Dodge,Matthew D. Zeiler,Xiaogang Wang +4 more
- 15 Jun 2019
TL;DR: A Category Traversal Module is introduced that can be inserted as a plug-and-play module into most metric-learning based few-shot learners, identifying task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space.
Fast Image Processing with Fully-Convolutional Networks
Qifeng Chen,Jia Xu,Vladlen Koltun +2 more
- 02 Sep 2017
TL;DR: In this article, a fully-convolutional network is trained on input-output pairs that demonstrate the operator's action, and the trained network operates at full resolution and runs in constant time.
397
Multi-Level Semantic Feature Augmentation for One-Shot Learning
TL;DR: This paper proposes a novel approach to one-shot learning that learns to map a novel sample instance to a concept, relates that concept to the existing ones in the concept space and, using these relationships, generates new instances by interpolating among the concepts to help learning.