{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T23:58:12Z","timestamp":1780617492548,"version":"3.54.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,1,30]],"date-time":"2021-01-30T00:00:00Z","timestamp":1611964800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,1,30]],"date-time":"2021-01-30T00:00:00Z","timestamp":1611964800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"This work was supported by the National Natural Science Foundation of China","award":["61771352"],"award-info":[{"award-number":["61771352"]}]},{"name":"the Science and Technology Innovation Team Project of Hubei Province.","award":["T201838"],"award-info":[{"award-number":["T201838"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2022,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Although convolutional neural networks have achieved success in the field of image classification, there are still challenges in the field of agricultural product quality sorting such as machine vision-based jujube defects detection. The performance of jujube defect detection mainly depends on the feature extraction and the classifier used. Due to the diversity of the jujube materials and the variability of the testing environment, the traditional method of manually extracting the features often fails to meet the requirements of practical application. In this paper, a jujube sorting model in small data sets based on convolutional neural network and transfer learning is proposed to meet the actual demand of jujube defects detection. Firstly, the original images collected from the actual jujube sorting production line were pre-processed, and the data were augmented to establish a data set of five categories of jujube defects. The original CNN model is then improved by embedding the SE module and using the triplet loss function and the center loss function to replace the softmax loss function. Finally, the depth pre-training model on the ImageNet image data set was used to conduct training on the jujube defects data set, so that the parameters of the pre-training model could fit the parameter distribution of the jujube defects image, and the parameter distribution was transferred to the jujube defects data set to complete the transfer of the model and realize the detection and classification of the jujube defects. The classification results are visualized by heatmap through the analysis of classification accuracy and confusion matrix compared with the comparison models. The experimental results show that the SE-ResNet50-CL model optimizes the fine-grained classification problem of jujube defect recognition, and the test accuracy reaches 94.15%. The model has good stability and high recognition accuracy in complex environments.<\/jats:p>","DOI":"10.1007\/s00521-021-05715-2","type":"journal-article","created":{"date-parts":[[2021,1,30]],"date-time":"2021-01-30T13:02:49Z","timestamp":1612011769000},"page":"3385-3398","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Classification of jujube defects in small data sets based on transfer learning"],"prefix":"10.1007","volume":"34","author":[{"given":"Jianping","family":"Ju","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyuan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaohui","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,30]]},"reference":[{"key":"5715_CR1","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.biosystemseng.2011.01.006","volume":"108","author":"K Wang","year":"2011","unstructured":"Wang K, Nakano S, Ohashi S (2011) Detection of external insect infestations in jujube fruit using hyperspectral reflectance imaging. Biosys Eng 108:345\u2013351","journal-title":"Biosys Eng"},{"issue":"4","key":"5715_CR2","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1016\/j.lwt.2010.11.012","volume":"44","author":"K Wang","year":"2010","unstructured":"Wang K, Nakano S, Ohashi S (2010) Nondestructive evaluation of jujube quality by visible and near-infrared spectroscopy. LWT - Food Sci Technol 44(4):1119\u20131125","journal-title":"LWT - Food Sci Technol"},{"key":"5715_CR3","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.postharvbio.2015.09.003","volume":"112","author":"L Wu","year":"2016","unstructured":"Wu L, He J, Liu G, Wang S, He X (2016) Detection of common defects on jujube using Vis-NIR and NIR hyperspectral imaging. Postharvest Biol Technol 112:134\u2013142","journal-title":"Postharvest Biol Technol"},{"key":"5715_CR4","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.jfoodeng.2007.10.021","volume":"86","author":"D Lee","year":"2008","unstructured":"Lee D, Schoenberger R, Archibald J (2008) Development of a machine vision system for automatic date grading using digital reflective near-infrared imaging. J Food Eng 86:388\u2013398","journal-title":"J Food Eng"},{"key":"5715_CR5","unstructured":"Li Y, Zhang Q, Chen H (2016) Detection of diseases and cracks of semi-dried dates based on machine vision. J Agric Mech Res 38:120\u2013125"},{"issue":"3","key":"5715_CR6","first-page":"113","volume":"39","author":"J Zhao","year":"2008","unstructured":"Zhao J (2008) Recognition of defect chinese dates by machine vision and support vector machine. Trans Chin Soc Agric Mach 39(3):113\u2013117","journal-title":"Trans Chin Soc Agric Mach"},{"key":"5715_CR7","first-page":"1089","volume":"28","author":"LT Zhang","year":"2016","unstructured":"Zhang LT, San-Min S (2016) Study on appearance quality classification based on detection of the striples of red jujube in Southern Xinjiang. Acta Agric Zhejiangensis 28:1089\u20131093","journal-title":"Acta Agric Zhejiangensis"},{"issue":"8","key":"5715_CR8","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1109\/MC.2016.245","volume":"49","author":"AV Dastjerdi","year":"2016","unstructured":"Dastjerdi AV, Buyya R (2016) Fog computing: helping the internet of things realize its potential. Computer 49(8):112\u2013116","journal-title":"Computer"},{"issue":"15","key":"5715_CR9","first-page":"219","volume":"33","author":"Y Zhou","year":"2017","unstructured":"Zhou Y (2017) Classification and recognition approaches of tomato main organs based on DCNN. Trans Chin Soc Agric Eng 33(15):219\u2013226","journal-title":"Trans Chin Soc Agric Eng"},{"issue":"6","key":"5715_CR10","first-page":"1073","volume":"30","author":"G Yang","year":"2018","unstructured":"Yang G, Xu N, Kang L, Gong M, Hong Z (2018) Identification of navel orange lesions leaves based on parametric exponential non-linear residual neural network. Acta Agric Zhejiangensis 30(6):1073\u20131081","journal-title":"Acta Agric Zhejiangensis"},{"key":"5715_CR11","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.3389\/fpls.2016.01419","volume":"7","author":"P Mohanty","year":"2016","unstructured":"Mohanty P, Hughes DP, Salath\u00e9 M (2016) Using deep learning for image-based plant disease detection. Front Plant Sci 7:1419","journal-title":"Front Plant Sci"},{"issue":"10","key":"5715_CR12","doi-asserted-by":"publisher","first-page":"661","DOI":"10.14358\/PERS.83.10.661","volume":"83","author":"T Charles","year":"2017","unstructured":"Charles T (2017) Photogrammetric computer vision: statistics, geometry, orientation and reconstruction. Photogram Eng Remote Sens 83(10):661\u2013662","journal-title":"Photogram Eng Remote Sens"},{"key":"5715_CR13","doi-asserted-by":"crossref","unstructured":"Hu J, Lu J, Tan YP (2015) Deep transfer metric learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 325\u2013333","DOI":"10.1109\/CVPR.2015.7298629"},{"issue":"1","key":"5715_CR14","first-page":"26","volume":"26","author":"FZ Zhuang","year":"2015","unstructured":"Zhuang FZ, Luo P, He Q, Shi ZZ (2015) Survey on transfer learning research. Ruan Jian Xue Bao\/J Softw 26(1):26\u201339","journal-title":"Ruan Jian Xue Bao\/J Softw"},{"key":"5715_CR15","doi-asserted-by":"publisher","unstructured":"Rodionov S, Potapov A, Latapie H, Fenoglio E, Peterson M (2018) Improving deep models of person re-identification for cross-dataset usage. Artif Intell Appl Innovations. https:\/\/doi.org\/10.1007\/978-3-319-92007-8_7","DOI":"10.1007\/978-3-319-92007-8_7"},{"key":"5715_CR16","unstructured":"Luo Y, Wen Y, Duan L-Y, Tao D (2018) Transfer metric learning: Algorithms, applications and outlooks. arXiv preprint arXiv:1810.03944"},{"key":"5715_CR17","doi-asserted-by":"publisher","unstructured":"Wei X, Chen Y, Su J (2018) Domain adaptation via identical distribution across models and tasks. Lecture Notes Comput Sci. https:\/\/doi.org\/10.1007\/978-3-030-04167-0_21","DOI":"10.1007\/978-3-030-04167-0_21"},{"issue":"4","key":"5715_CR18","doi-asserted-by":"publisher","first-page":"041001","DOI":"10.3788\/LOP53.041001","volume":"53","author":"Z Huang","year":"2016","unstructured":"Huang Z, Zhu Q (2016) Detection of red region of Fuji Apple based on RGB color model. Laser Optoelectron Progress 53(4):041001","journal-title":"Laser Optoelectron Progress"},{"key":"5715_CR19","unstructured":"Peiying C (2009) A novel OSTU segmentation algorithm for image threshold. Comput Appl Softw 2009(5):227\u2013232"},{"key":"5715_CR20","doi-asserted-by":"publisher","first-page":"55501","DOI":"10.1109\/ACCESS.2018.2871729","volume":"6","author":"Z Zheng","year":"2018","unstructured":"Zheng Z, Ma Y, Zheng H, Ju J, Lin M (2018) UGC: real-time, ultra-robust feature correspondence via unilateral grid-based clustering. IEEE Access 6:55501\u201355508","journal-title":"IEEE Access"},{"issue":"5","key":"5715_CR21","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1080\/00288230709510361","volume":"50","author":"M Sun","year":"2007","unstructured":"Sun M, Si J, Zhang S (2007) Research on embedding and extracting methods for digital watermarks applied to QR code images. NZ J Agric Res 50(5):861\u2013867","journal-title":"NZ J Agric Res"},{"issue":"6","key":"5715_CR22","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1109\/JSTARS.2014.2329330","volume":"7","author":"Y Chen","year":"2014","unstructured":"Chen Y, Lin Z, Zhao X, Wang G, Gu Y (2014) Deep learning-based classification of hyperspectral data. IEEE J Sel Top Appl Earth Observ Remote Sens 7(6):2094\u20132107","journal-title":"IEEE J Sel Top Appl Earth Observ Remote Sens"},{"key":"5715_CR23","doi-asserted-by":"crossref","unstructured":"He K (2016) Deep residual learning for image recognition. IEEE conference on computer vision & pattern recognition.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"11","key":"5715_CR24","doi-asserted-by":"publisher","first-page":"S329","DOI":"10.1016\/j.spinee.2017.10.044","volume":"17","author":"C Perkins","year":"2017","unstructured":"Perkins C, Moideen AN, Ahuja S (2017) Return to activity and sports following posterior correction and fusion for adolescent idiopathic scoliosis. The Spine J 17(11):S329\u2013S330","journal-title":"The Spine J"},{"issue":"6","key":"5715_CR25","doi-asserted-by":"publisher","first-page":"3512","DOI":"10.1109\/TGRS.2018.2885506","volume":"57","author":"W Ma","year":"2019","unstructured":"Ma W (2019) Achieving super-resolution remote sensing images via the wavelet transform combined with the recursive res-net. IEEE Trans Geosci Remote Sens 57(6):3512\u20133527","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"5715_CR26","first-page":"S10538119173033","volume":"170","author":"H Chen","year":"2017","unstructured":"Chen H (2017) VoxResNet: deep voxelwise residual networks for brain segmentation from 3D MR images. Neuroimage 170:S1053811917303348","journal-title":"Neuroimage"},{"key":"5715_CR27","unstructured":"Jie H (2017) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell, pp 99"},{"key":"5715_CR28","first-page":"1229","volume":"40","author":"FY Zhou","year":"2017","unstructured":"Zhou FY, Jin LP, Dong J (2017) Review of convolutional neural network. Chin J Comput 40:1229\u20131251","journal-title":"Chin J Comput"},{"key":"5715_CR29","unstructured":"Liu W (2016) Large-margin softmax loss for convolutional neural networks"},{"key":"5715_CR30","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Face net: a unified embedding for face recognition and clustering. In: IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7298682"},{"issue":"10","key":"5715_CR31","doi-asserted-by":"publisher","first-page":"4806","DOI":"10.1109\/TIP.2017.2695101","volume":"26","author":"F Zhu","year":"2017","unstructured":"Zhu F (2017) Part-based deep hashing for large-scale person re-identification. IEEE Trans Image Process 26(10):4806\u20134817","journal-title":"IEEE Trans Image Process"},{"key":"5715_CR32","doi-asserted-by":"crossref","unstructured":"Lei H (2018) A deeply supervised residual network for HEp-2 cell classification via cross-modal transfer learning. Pattern Recognit, 79.","DOI":"10.1016\/j.patcog.2018.02.006"},{"key":"5715_CR33","doi-asserted-by":"crossref","unstructured":"Wen Y, Zhang K, Li Z (2016) A discriminative feature learning approach for deep face recognition. In: ECCV","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"5715_CR34","doi-asserted-by":"crossref","unstructured":"He X (2018) Triplet-center loss for multi-view 3D object retrieval. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00208"},{"issue":"2","key":"5715_CR35","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1109\/TIP.2015.2502147","volume":"25","author":"L Zhang","year":"2015","unstructured":"Zhang L (2015) Detecting densely distributed graph patterns for fine-grained image categorization. IEEE Trans Image Process 25(2):553\u2013565","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"5715_CR36","first-page":"26","volume":"26","author":"FZ Zhuang","year":"2015","unstructured":"Zhuang FZ, Luo P, He Q, Shi ZZ (2015) Survey on transfer learning research. Ruan Jian Xue Bao\/J Softw 26(1):26\u201339","journal-title":"Ruan Jian Xue Bao\/J Softw"},{"key":"5715_CR37","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva (2016) Learning deep features for discriminative localization. In: IEEE conference on computer vision and pattern recognition, pp.2921\u20132929.","DOI":"10.1109\/CVPR.2016.319"},{"key":"5715_CR38","doi-asserted-by":"crossref","unstructured":"Selvaraju RR (2016) Grad-CAM: visual explanations from deep networks via gradient-based localization. In: International conference on computer vision and pattern recognitions","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05715-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-05715-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05715-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T06:31:56Z","timestamp":1645684316000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-05715-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,30]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["5715"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-05715-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,30]]},"assertion":[{"value":"29 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"These no potential competing interests in our paper. And all authors have seen the manuscript and approved to submit to your journal. We confirm that the content of the manuscript has not been published or submitted for publication elsewhere.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}