Deep Innovation Processing Laboratory · KMITL

Teaching machines to see, hear, and understand.

DIP Lab at KMITL builds neural systems for computer vision, language, and speech — and shares the research in the open.

Explore research Read the papers

24+
Publications: 15
Researchers: 4
Research areas

Featured project

Reflection Removal and Facial Detection of Individuals in Vehicles

Completed

Research areas

Four directions where we push the state of the art — from pixels to language to the systems that train them.

Computer Vision

Advanced image reconstruction, recognition, and segmentation.

Generative AI & NLP

Large language models (LLM) and multimodal learning (MLLM).

Speech Processing

State-of-the-art TTS and ASR technologies.

AI Infrastructure

Specialized computing environments for massive-scale training.

Latest projects

View all

Completed

Reflection Removal and Facial Detection of Individuals in Vehicles

The research, “Reflection Removal and Facial Detection of Individuals in Vehicles,” utilizes Single Image Reflection Removal (SIRR) technology and Face Detection to remove reflections and reduce glare caused by automotive glass and film. This enables the capture of facial images of individuals inside vehicles. SIRR technology enhances image quality by removing reflections from the surfaces of glass that might obscure objects. In this research, we explore the use of three models specialized in SIRR and YOLOv7 for Face Detection. However, the pre-trained models for reflection removal failed to effectively remove reflections and reduce glare from films. In this paper, we propose an approach to enhance the efficiency of removing reflections and reducing glare caused by automotive glass and film with opacities set at 40% and 60%, achieving an impressive improvement in Peak Signal-to-Noise Ratio (PSNR) by approximately 42.96% and Structural Similarity Index (SSIM) by approximately 34.16% compared to the pre-trained models.