Object Detection with Audio Comments using YOLO v3

Gupta, Sneha; Chakraborti, Suchismita; Yogitha, R.; Mathivanan, G.

doi:10.1109/icaaic53929.2022.9792755

Cited by 3 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A pivotal innovation is the use of the user's hand as a reference point. By detecting the user's hand and identifying target objects within the camera's view, the system guides users to the object's location using imageto-speech techniques [7]. Furthermore, we have devised algorithms to deliver directional guidance and distance information, complemented by auditory feedback.…”

Section: Related Workmentioning

confidence: 99%

Audio Enabled Object Detection System with NLP based Interaction

Chakrapani

2024

IJSREM

View full text Add to dashboard Cite

The project aims to develop an innovative object detection system that uses audio input and output to enhance user engagement and provide detailed product information. The system employs deep learning techniques for real-time object identification, generating an audio-based output with the object's name. In order to enable users to interact with the system verbally, it also incorporates Natural Language Processing (NLP), which interprets and processes speech in order to identify the object. The system also includes an online search module, which provides users with descriptions of the object's attributes and potential applications. The system undergoes rigorous testing and optimization to ensure accuracy and responsiveness. The project employs user-friendly technology that can assist people with low vision or disabilities, providing a practical and time-saving alternative for seeking instant information about objects. In order to make object recognition and information retrieval a smooth and inclusive experience for all users, this audio-enabled system is a first step towards bridging the gap between artificial intelligence and human-technology interaction. Key Words: Object Detection, Natural Language Processing, YOLOv4, Google Gemini, MeaningCloud, Wikipedia library

show abstract

Section: Related Workmentioning

confidence: 99%

Audio Enabled Object Detection System with NLP based Interaction

Chakrapani

2024

IJSREM

View full text Add to dashboard Cite

show abstract

“…The application areas of YOLO are very wide. For example, in the medical field, related identification applications include cervical cancer [ 13 ], blood cells [ 14 ], colorectal cancer [ 15 ], venipuncture [ 16 ], etc., Applications also include the auxiliaries for hearing and visually impaired people [ 17 ] and sign language identification [ 18 ]. Furthermore, due to the influence of epidemics, there were many mask identification studies based on the use of different algorithms [ 19 , 20 , 21 , 22 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Clothing Style Recognition Using YOLOv5

Chang

Zhang

2022

Micromachines

View full text Add to dashboard Cite

With the rapid development of artificial intelligence, much more attention has been paid to deep learning. However, as the complexity of learning algorithms increases, the needs of computation power of hardware facilities become more crucial. Instead of the focus being on computing devices like GPU computers, a lightweight learning algorithm could be the answer for this problem. Cross-domain applications of deep learning have attracted great interest amongst researchers in academia and industries. For beginners who do not have enough support with software and hardware, an open-source development environment is very helpful. In this paper, a relatively lightweight algorithm YOLOv5s is addressed, and the Google Colab is used for model training and testing. Based on the developed environment, many state-of-art learning algorithms can be studied for performance comparisons. To highlight the benefits of one-stage object detection algorithms, the recognition of clothing styles is investigated. The image samples are selected from datasets of fashion clothes and the web crawling of online stores. The image data are categorized into five groups: plaid; plain; block; horizontal; and vertical. Average precison, mean average precison, recall, F1-score, model size, and frame per second are the metrics used for performance validations. From the experimental outcomes, it shows that YOLOv5s is better than other learning algorithms in the recognition accuracy and detection speed.

show abstract