Scribd
Upload
116 views2 pages

Solar Cell Defect Detection with YOLOv5

The document presents a project on an optimized YOLOv5 model for detecting defects in solar cells, addressing issues of low accuracy in traditional methods. It incorporates five data enhancement techniques and a CA attention mechanism to improve feature extraction and robustness. Additionally, it replaces the original detection head with a decoupling head to enhance classification and localization accuracy without compromising convergence speed.

Uploaded by

ogiridharreddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
116 views2 pages

Solar Cell Defect Detection with YOLOv5

The document presents a project on an optimized YOLOv5 model for detecting defects in solar cells, addressing issues of low accuracy in traditional methods. It incorporates five data enhancement techniques and a CA attention mechanism to improve feature extraction and robustness. Additionally, it replaces the original detection head with a decoupling head to enhance classification and localization accuracy without compromising convergence speed.

Uploaded by

ogiridharreddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

VISVESVARAYA TECHNOLOGICAL UNIVERSITY

“JNANA SANGAMA” BELAGAVI- 590018, KARNATAKA

“Solar Cell Surface Defect Detection Based on Optimized YOLOv5”

Submitted in the partial fulfilment of the requirement for the award of degree of
BACHELOR OF ENGINEERING
IN
COMPUTER SCIENCE AND ENGINEERING BY

Peram Rakesh Reddy 1RL21CS084

Obili Giridhar Reddy 1RL21CS077

Kuruva Uday Kiran 1RL21CS054

Under the Guidance of


G M Anand Reddy
Associate Professor, Dept of CSE, RLJIT

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

R L JALAPPA INSTITUTE OF TECHNOLOGY


DODDABALLAPUR-561 203 (KARNATAKA) 2024-2025
Solar Cell Surface Defect Detection Based on Optimized YOLOv5

Abstract

Traditional vision methods for solar cell defect detection have problems such as low accuracy
and few types of detection, so this project proposes an optimized YOLOv5 model for more
accurate and comprehensive identification of defects in solar cells. The model firstly integrates
five data enhancement methods, namely Mosaic, Mixup, hsv transform, scale transform and flip,
to expand the existing data set to improve the feature training accuracy and enhance the
robustness of the model; secondly, CA attention mechanism is introduced to improve the feature
extraction ability of the model; to address the problems of different target defect classification
and localization concerns, the detection head in the original model is replaced with a decoupling
head, which significantly improve the detection accuracy of the model without affecting the
convergence speed of the mode

You might also like