Browsing by Author "Weerasinghe, K. M. L. P"

Now showing 1 - 2 of 2

Embargo
eVision - A technological solution to assist vision impaired in self-navigation
(IEEE, 2022-07-18) Hewagama, K. G; Suwandarachchi, T. D; Hettiarachchi, C. R; Alwis, P. L. D. N; Karunasena, A; Weerasinghe, K. M. L. P
Visually impaired people face many difficulties in navigation such as crossing the road, identifying signs and text in indoor and outdoor environments and avoiding obstacles. Even though much research has been done to assist visually impaired people, most methods are unpopular, and almost all visually impaired people still only rely on the white cane. This paper proposes eVision which consists of a mobile app as well as a wearable tool that enables visually impaired people to detect obstacles and objects such as moving vehicles and staircases, identify signs, provide assistance with road crossing and natural scene text recognition, using Convolutional Neural Networks and image processing techniques. The CNN architecture used for object detection was SSD Mobilenet V2, since it provided around 95% accuracy for most objects with good performance on mobile. Mobilenet V2 transfer learning model was used for classification of objects, which provided around 94% accuracy. For text detection, the EAST algorithm was used, and the method resulted an accuracy around 98%. From the generated data from models, eVision provides audio feedback to the user using a text to speech(TTS) system.
Embargo
Virtual Makeover and Makeup Recommendation Based on Personal Trait Analysis
(IEEE, 2021-12-09) Perera, P. R. H; Soysa, E. S. S; De Silva, H. R. S; Tavarayan, A. R. P; Gamage, M. P; Weerasinghe, K. M. L. P
The utilization of facial makeup is an important attribute in modern society as a means of self-expression, and as a method to feel more confident during social interactions. A makeover has become a necessity when attending divergent functions, and makeup used on diverse occasions varies in style. Choosing the perfect makeup that best suits a person is challenging unless they have years of expertise with cosmetics. This paper proposes a “Virtual Makeover and Makeup Recommendation System” to eliminate the need to be concerned about the appearance after applying makeup. The proposed system enables real-time makeup simulation in an Augmented Reality (AR) environment and recommends makeup styles considering skin tone, colour of clothing and hair, type of clothing and occasion to be attended with makeup. The personal traits of a user would be automatically detected and processed to generate recommendations for makeup products, namely lipstick, foundation and eyeshadow. Complications of wasting makeup products and time, and cleaning makeup can be mitigated by using a real-time makeup simulation system. Recommendations generated by the application assist the users to decide on makeup styles and provides a better user experience. The proposed system is developed with the aid of Deep Learning (DL) algorithms.