@Article{cmc.2020.010039, AUTHOR = {Shuqiang Guo, Baohai Yue, Manyang Gao, Xinxin Zhou, Bo Wang}, TITLE = {Classification for Glass Bottles Based on Improved Selective Search Algorithm}, JOURNAL = {Computers, Materials \& Continua}, VOLUME = {64}, YEAR = {2020}, NUMBER = {1}, PAGES = {233--251}, URL = {http://www.techscience.com/cmc/v64n1/39140}, ISSN = {1546-2226}, ABSTRACT = {The recycling of glass bottles can reduce the consumption of resources and contribute to environmental protection. At present, the classification of recycled glass bottles is difficult due to the many differences in specifications and models. This paper proposes a classification algorithm for glass bottles that is divided into two stages, namely the extraction of candidate regions and the classification of classifiers. In the candidate region extraction stage, aiming at the problem of the large time overhead caused by the use of the SIFT (scale-invariant feature transform) descriptor in SS (selective search), an improved feature of HLSN (Haar-like based on SPP-Net) is proposed. An integral graph is introduced to accelerate the process of forming an HBSN vector, which overcomes the problem of repeated texture feature calculation in overlapping regions by SS. In the classification stage, the improved SS algorithm is used to extract target regions. The target regions are merged using a non-maximum suppression algorithm according to the classification scores of the respective regions, and the merged regions are classified using the trained classifier. Experiments demonstrate that, compared with the original SS, the improved SS algorithm increases the calculation speed by 13.8%, and its classification accuracy is 89.4%. Additionally, the classification algorithm for glass bottles has a certain resistance to noise.}, DOI = {10.32604/cmc.2020.010039} }