Naosekpam
Doctoral student working in the domain of Computer Vision and Deep Learning
Indian Institute of Information Technology GuwahatiIndia
Pinned Repositories
Computer-Vision-resources
Slides related to classification and object detection
EMBiL-English-Manipuri-Benchmark-for-scene-text-detection-and-language-identification
A curated bi-lingual scene text detection and language identification benchmark dataset named EMBiL, comprising English and Manipuri texts embedded in the scene images. The paper is accepted at CAIP ' 23.
Hate-speech-detection
IIITG-MLRIT2022-Scene-Text
A multi-label language identification dataset based on regional Indian languages. It contains 5 languages (Hindi, Bengali, Malayalam, Kannada, and English) with the presence of two scripts per image (implying the multi-linguality). The dataset is diverse in nature with the existence of curved, perspective distorted, and multi-oriented text in addition to the horizontal text. This diversity is achieved by applying various image transformation techniques such as affine, arcs, and perspective distortion with different angular degrees. The dataset is harvested from multiple sources: captured from mobile cameras, existing datasets, and web sources.
Image-Alignment-and-Warping
Intermediate-Features-Fusion-based-CNN
LocalRepo
Machine-learning-in-3D-space-gesture-recognition
HCI application where hand movement of an English alphabet is captured by an accelerometer and display the corresponding letter on the screen.
Multi-lingual-Indian-text-detector-for-mobile-devices
Scene text detection on Indian scene text data using shallow version of YOLO v3 and v4
Superpixel-based-non-parametric-scene-parsing
Context based non-parametric solution to the scene parsing problem based on partial correspondence.
Naosekpam's Repositories
Naosekpam/EMBiL-English-Manipuri-Benchmark-for-scene-text-detection-and-language-identification
A curated bi-lingual scene text detection and language identification benchmark dataset named EMBiL, comprising English and Manipuri texts embedded in the scene images. The paper is accepted at CAIP ' 23.
Naosekpam/Intermediate-Features-Fusion-based-CNN
Naosekpam/Computer-Vision-resources
Slides related to classification and object detection
Naosekpam/Hate-speech-detection
Naosekpam/IIITG-MLRIT2022-Scene-Text
A multi-label language identification dataset based on regional Indian languages. It contains 5 languages (Hindi, Bengali, Malayalam, Kannada, and English) with the presence of two scripts per image (implying the multi-linguality). The dataset is diverse in nature with the existence of curved, perspective distorted, and multi-oriented text in addition to the horizontal text. This diversity is achieved by applying various image transformation techniques such as affine, arcs, and perspective distortion with different angular degrees. The dataset is harvested from multiple sources: captured from mobile cameras, existing datasets, and web sources.
Naosekpam/Image-Alignment-and-Warping
Naosekpam/LocalRepo
Naosekpam/Machine-learning-in-3D-space-gesture-recognition
HCI application where hand movement of an English alphabet is captured by an accelerometer and display the corresponding letter on the screen.
Naosekpam/Multi-lingual-Indian-text-detector-for-mobile-devices
Scene text detection on Indian scene text data using shallow version of YOLO v3 and v4
Naosekpam/Superpixel-based-non-parametric-scene-parsing
Context based non-parametric solution to the scene parsing problem based on partial correspondence.
Naosekpam/spaghetti
SPAtial GrapHs: nETworks, Topology, & Inference