Automatic classification of textile visual pollutants using deep learning networks

Tasnim, Najia Hasan; Afrin, Sadia; Biswas, Barna; Anye, Arifa Akter; Khan, Riasat

doi:10.1016/j.aej.2022.07.039

Cited by 21 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sistem inspeksi cacat pada permukaan kayu dengan model deteksi objek YOLOv5 [2]. Penelitian serupa juga dilakukan oleh dengan menggunakan berbagai macam metode antara lain integrasi antara YOLOv5 dan ResNet [7], deep learning [8,9], integrasi antara machine learning dan deep learning [10], FE-YOLOv5 [11], serta YOLOv3 [12]. Selain itu, Aplikasi untuk mendeteksi kualitas daging dikembangkan dengan mengaplikasikan region of interest (ROI) [13].…”

Section: Pendahuluanunclassified

Deteksi Cacat pada Sekrup Berbasis Citra Menggunakan YOLOv5

2024

jikstik

View full text Add to dashboard Cite

Perusahaan pasti menginginkan produk yang dihasilkannya berkualitas baik. Kenyataannya kecacatan produk merupakan hal yang sulit dihindari. Kegiatan pengendalian kualitas diperlukan untuk mencegah produk cacat sampai kepada pelanggan. Pengendalian kualitas yang dilakukan manual membutuhkan waktu yang lama dengan tingkat subjektias serta resiko human error yang tinggi. Pemanfaatan teknologi dibutuhkan untuk membantu kegiatan pengendalian kualitas. Teknologi yang dapat dimanfaatkan untuk pengendalian kualitas adalah Articial Intelligence (AI) dengan metode deep learning menggunakan arsitektur YOLOv5. Tujuan penelitian ini adalah mengembangkan model yang dapat mendeteksi kualitas sekrup berbasis citra. Pengolahan data dilakukan dengan Roboow untuk proses preprocessing. Proses pembuatan model menggunakan Google Colab dengan bahasa pemrograman python. Hasil penelitian menunjukkan pelatihan mendapatkan waktu pelatihan sebesar 0.404 jam atau 24.24 menit, precision 0.842, recall 0.857, dan mean average precision 0.887. Uji coba yang dilakukan menghasilkan bahwa citra dapat terdeteksi dengan baik. Namun, terdapat beberapa citra yang kurang baik dan maksimal untuk dideteksi.

show abstract

Section: Pendahuluanunclassified

Deteksi Cacat pada Sekrup Berbasis Citra Menggunakan YOLOv5

2024

jikstik

View full text Add to dashboard Cite

show abstract

“…Tasnim et al [21] delved into the application of computer vision techniques to develop an innovative approach for the automatic detection and categorization of visual pollutants associated with the textile industry. Their research focused on three categories of textilebased visual pollutants: cloth litter, advertising billboards, signs, and textile dyeing waste materials.…”

Section: Related Workmentioning

confidence: 99%

Deep-Learning-Based Real-Time Visual Pollution Detection in Urban and Textile Environments

Titu,

Chowdhury,

Haque

et al. 2024

Sci

Self Cite

View full text Add to dashboard Cite

The environmental physiognomy of an area can significantly diminish its aesthetic appeal, rendering it susceptible to visual pollution, the unbeaten scourge of modern urbanization. In this study, we propose using a deep learning network and a robotic vision system integrated with Google Street View to identify streets and textile-based visual pollution in Dhaka, the megacity of Bangladesh. The issue of visual pollution extends to the global apparel and textile industry, as well as to various common urban elements such as billboards, bricks, construction materials, street litter, communication towers, and entangled electric wires. Our data collection encompasses a wide array of visual pollution elements, including images of towers, cables, construction materials, street litter, cloth dumps, dyeing materials, and bricks. We employ two open-source tools to prepare and label our dataset: LabelImg and Roboflow. We develop multiple neural network models to swiftly and accurately identify and classify visual pollutants in this work, including Faster SegFormer, YOLOv5, YOLOv7, and EfficientDet. The tuna swarm optimization technique has been used to select the applied models’ final layers and corresponding hyperparameters. In terms of hardware, our proposed system comprises a Xiaomi-CMSXJ22A web camera, a 3.5-inch touchscreen display, and a Raspberry Pi 4B microcontroller. Subsequently, we program the microcontroller with the YOLOv5 model. Rigorous testing and trials are conducted on these deep learning models to evaluate their performance against various metrics, including accuracy, recall, regularization and classification losses, mAP, precision, and more. The proposed system for detecting and categorizing visual pollution within the textile industry and urban environments has achieved notable results. Notably, the YOLOv5 and YOLOv7 models achieved 98% and 92% detection accuracies, respectively. Finally, the YOLOv5 technique has been deployed into the Raspberry Pi edge device for instantaneous visual pollution detection. The proposed visual pollutants detection device can be easily mounted on various platforms (like vehicles or drones) and deployed in different urban environments for on-site, real-time monitoring. This mobility is crucial for comprehensive street-level data collection, potentially engaging local communities, schools, and universities in understanding and participating in environmental monitoring efforts. The comprehensive dataset on visual pollution will be published in the journal following the acceptance of our manuscript.

show abstract

“… Chen et al [ 21 ] 2023 ShuffleNet v2- depth-separable convolution model Recyclable waste classification Formulating a combined classification approach based on ShuffleNet v2 and the depth-separable convolution model, enabling efficient classification of recyclable waste. Tasnim et al [ 22 ] 2023 Deep learning Pollutants associated with textiles Introducing an advanced deep learning classifier called EfficientNet, which outperformed KNN and CNN models in detecting and categorizing visual pollutants associated with textiles, including cloth waste, dyeing materials, and advertising displays. Luo et al [ 23 ] 2023 CNN Weed seeds classification Investigating various CNN model structures to determine the most effective approach for classifying weed seeds.…”

Section: Introductionmentioning

confidence: 99%

A reliable jumping-based classification methodology for environment sector

Etemadi,

Khashei,

Hamadani

et al. 2024

Heliyon

View full text Add to dashboard Cite

Automatic classification of textile visual pollutants using deep learning networks

Cited by 21 publications

References 24 publications

Deteksi Cacat pada Sekrup Berbasis Citra Menggunakan YOLOv5

Deteksi Cacat pada Sekrup Berbasis Citra Menggunakan YOLOv5

Deep-Learning-Based Real-Time Visual Pollution Detection in Urban and Textile Environments

A reliable jumping-based classification methodology for environment sector

Contact Info

Product

Resources

About