Similarity Analysis Model with 6CH ResNet Structure
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Largescale waste similarity analysis is crucial for automating waste management on a large scale. It involvesconfirming the match between waste discharged from homes and that collected by agencies, which is essentialfor a stable automated system. This paper compares feature extraction methods for similarity measurement,including the scaleinvariant feature transform (SIFT) algorithm with added HSV color features, convolutionalneural networkbased encoders, and a modified 6channel (6CH) ResNet for endtoend learning. The resultsdemonstrate that the 6CH ResNet achieves up to 4.9% higher accuracy than both the basic SIFT method andencoders, as well as the SIFT algorithm with HSV color features. Implementing the 6CH ResNet in automatedwaste management systems can enhance object similarity measurement while using fewer computing resources.
Abstract
Largescale waste similarity analysis is crucial for automating waste management on a large scale. It involvesconfirming the match between waste discharged from homes and that collected by agencies, which is essentialfor a stable automated system. This paper compares feature extraction methods for similarity measurement,including the scaleinvariant feature transform (SIFT) algorithm with added HSV color features, convolutionalneural networkbased encoders, and a modified 6channel (6CH) ResNet for endtoend learning. The resultsdemonstrate that the 6CH ResNet achieves up to 4.9% higher accuracy than both the basic SIFT method andencoders, as well as the SIFT algorithm with HSV color features. Implementing the 6CH ResNet in automatedwaste management systems can enhance object similarity measurement while using fewer computing resources.
참고문헌 (9)
- V. Muneeswaran, "Smart segregation of waste and automatic monitoring system", Proceedings of 2023 International Conference on Computer Communication and Informatics (ICCCI), pp.1~6 (2023)
- T. Ji, "Automatic sorting of low-value recyclable waste : a comparative experimental study", Clean Technologies and Environmental Policy, 25(3), pp.949~961 (2023)[DOI]
- L. Marlinda, "Comparison of sift and orb methods in identifying the face of Buddha statue", JITK(Jurnal Ilmu Pengetahuan dan Teknologi Komputer), 8(2), pp.145~150 (2023)[DOI]
- A. Higaki, "Image similarity-based cardiac rhythm device identification from X-rays using feature point matching", Pacing and Clinical Electrophysiology, 44(4), pp.633~640 (2021)[DOI]
- M. Liang, "An unsupervised learning method with convolutional auto-encoder for vessel trajectory similarity computation", Ocean Engineering, 225 (2021)[DOI]
- "Image matching using SIFT, SURF, BRIEF and ORB: performance comparison for distorted images" (2017)[URL]
- K. Rama, "Deep autoencoders for feature learning with embeddings for recommendations : a novel recommender system solution", Neural Computing and Applications, 33(21), pp.14167~14177 (2021)[DOI]
- "Masked autoencoders that listen" (2022)[URL]
- A. Gogna, "Discriminative autoencoder for feature extraction : application to character recognition", Neural Processing Letters, 49, pp.1723~1735 (2019)[DOI]