Articles written in Sadhana
Volume 45 All articles Published: February 2020 Article ID 0040 Original Article (Computer Sciences)
A real-time fast defogging system to clear the vision of driver in foggy highway using minimum filter and gamma correction
GOURANGA MANDAL PARTHASARATHI DE DIPTENDU BHATTACHARYA
Fog is the most hindrance and unavoidable problem faced by drivers while driving. Due to foggy condition and poor visibility, especially in early morning and late-night, drivers are unable to see distant object on the road. As a result, possibility of road accident increases. In this article, a fast-real-time vision-baseddefogging system is proposed to clear the vision of highway during driving in the foggy environmental condition. The proposed system can remove the haziness of the driver’s vision and can present a clear view of the road within a very short span of time. Processing of each frame is comprised of four steps: calculation ofatmospheric light using minimum filter, transmission map, scene radiance and finally gamma correction is applied for removing the haziness with perfect contrast adjustment. In order to reduce time complexity, instead of estimating atmospheric light for each frame, it is calculated at an interval of 5000 frames. Many real-timeheuristic tests have been conducted during day as well at night on the highway and test analysis reveals that, after defogging, the distance of visibility increases by more than 65% during heavy fog. Besides, there is a massive increase in visibility during low foggy condition also.
Volume 47 All articles Published: 26 August 2022 Article ID 0177
Time efficient real time facial expression recognition with CNN and transfer learning
TANUSREE PODDER DIPTENDU BHATTACHARYA ABHISHEK MAJUMDAR
This study aims to design a real-time application to detect several human beings’ universal emotional levels simultaneously. The intra-class and inter-class variations present in images make it one of the most challenging recognition problems. In this regard, a simple solution for facial expression recognition using a combination of convolutional neural network (CNN) with minimal parameters and transfer learning (TL) has been proposed here. The proposed CNN architecture named LiveEmoNet has been jointly trained with wild (FER-2013) and lab-controlled (CK+) datasets for real-time detection, contributing to versatile emotion detection. The observed experimental results demonstrate that the proposed method outperforms the other related researche concerning accuracy and time. The accuracy of 68.93%, 97.66%, and 96.67% has been achieved on FER-2013, JAFFE, and 7-classes of the CK+ dataset, respectively. Also, real-time detection takes 46.85 ms/frame with an intel i5 2.60 GHz CPU, which is significantly better than other works in the literature.
Volume 48, 2023
Continuous Article Publishing mode
Click here for Editorial Note on CAP Mode