{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T03:58:31Z","timestamp":1777694311776,"version":"3.51.4"},"reference-count":39,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T00:00:00Z","timestamp":1714089600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ICA"],"published-print":{"date-parts":[[2024,4,26]]},"abstract":"<jats:p>In this paper, we propose a new method of representing images using highly compressed features for classification and image content retrieval \u2013 called PCA-ResFeats. They are obtained by fusing high- and low-level features from the outputs of ResNet-50 residual blocks and applying to them principal component analysis, which leads to a significant reduction in dimensionality. Further on, by applying a floating-point compression, we are able to reduce the memory required to store a single image by up to 1,200 times compared to jpg images and 220 times compared to features obtained by simple output fusion of ResNet-50. As a result, the representation of a single image from the dataset can be as low as 35 bytes on average. In comparison with the classification results on features from fusion of the last ResNet-50 residual block, we achieve a comparable accuracy (no worse than five percentage points), while preserving two orders of magnitude data compression. We also tested our method in the content-based image retrieval task, achieving better results than other known methods using sparse features. Moreover, our method enables the creation of concise summaries of image content, which can find numerous applications in databases.<\/jats:p>","DOI":"10.3233\/ica-230729","type":"journal-article","created":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T11:54:02Z","timestamp":1703850842000},"page":"267-284","source":"Crossref","is-referenced-by-count":5,"title":["Highly compressed image representation for classification and content retrieval"],"prefix":"10.1177","volume":"31","author":[{"given":"Stanis\u0142aw","family":"\u0141a\u017cewski","sequence":"first","affiliation":[]},{"given":"Bogus\u0142aw","family":"Cyganek","sequence":"additional","affiliation":[]}],"member":"179","reference":[{"issue":"2","key":"10.3233\/ICA-230729_ref2","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"International Journal of Computer Vision"},{"issue":"6","key":"10.3233\/ICA-230729_ref3","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1109\/72.329686","article-title":"A parallel genetic\/neural network learning algorithm for MIMD shared memory machines","volume":"5","author":"Hung","year":"1994","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"1","key":"10.3233\/ICA-230729_ref4","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/0925-2312(94)90033-7","article-title":"Object-oriented backpropagation and its application to structural design","volume":"6","author":"Hung","year":"1994","journal-title":"Neurocomputing"},{"issue":"3","key":"10.3233\/ICA-230729_ref6","doi-asserted-by":"crossref","first-page":"277","DOI":"10.3233\/ICA-220677","article-title":"Cognitive twin construction for system of systems operation based on semantic integration and high-level architecture","volume":"29","author":"Li","year":"2022","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"2","key":"10.3233\/ICA-230729_ref7","doi-asserted-by":"crossref","first-page":"141","DOI":"10.3233\/ICA-210672","article-title":"Perceptual metric-guided human image generation","volume":"29","author":"Wu","year":"2022","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"04","key":"10.3233\/ICA-230729_ref8","doi-asserted-by":"crossref","first-page":"2250016","DOI":"10.1142\/S0129065722500162","article-title":"Uncertainty-guided voxel-level supervised contrastive learning for semi-supervised medical image segmentation","volume":"32","author":"Hua","year":"2022","journal-title":"International Journal of Neural Systems"},{"issue":"09","key":"10.3233\/ICA-230729_ref9","doi-asserted-by":"crossref","first-page":"2250043","DOI":"10.1142\/S0129065722500435","article-title":"An efficient semi-supervised framework with multi-task and curriculum learning for medical image segmentation","volume":"32","author":"Wang","year":"2022","journal-title":"International Journal of Neural Systems"},{"key":"10.3233\/ICA-230729_ref10","doi-asserted-by":"crossref","first-page":"8675","DOI":"10.1007\/s00521-019-04359-7","article-title":"A dynamic ensemble learning algorithm for neural networks","volume":"32","author":"Alam","year":"2020","journal-title":"Neural Computing and Applications"},{"issue":"07","key":"10.3233\/ICA-230729_ref13","doi-asserted-by":"crossref","first-page":"2250030","DOI":"10.1142\/S0129065722500307","article-title":"Masked transformer for image anomaly localization","volume":"32","author":"De Nardin","year":"2022","journal-title":"International Journal of Neural Systems"},{"key":"10.3233\/ICA-230729_ref15","doi-asserted-by":"crossref","first-page":"103811","DOI":"10.1016\/j.imavis.2019.09.002","article-title":"ResFeats: Residual network based features for underwater image classification","volume":"93","author":"Mahmood","year":"2020","journal-title":"Image and Vision Computing"},{"issue":"2065","key":"10.3233\/ICA-230729_ref16","first-page":"1","article-title":"Principal component analysis: A review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Philos Trans A Math Phys Eng Sci"},{"issue":"12","key":"10.3233\/ICA-230729_ref18","doi-asserted-by":"crossref","first-page":"2674","DOI":"10.1109\/TVCG.2014.2346458","article-title":"Fixed-rate compressed floating-point arrays","volume":"20","author":"Lindstrom","year":"2014","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"10.3233\/ICA-230729_ref20","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107 R, Zisserman A. Three things everyone should know to improve object retrieval. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2012. pp.\u00a02911\u20132918.","DOI":"10.1109\/CVPR.2012.6248018"},{"issue":"5","key":"10.3233\/ICA-230729_ref25","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1109\/TPAMI.2009.77","article-title":"DAISY: An efficient dense descriptor applied to wide-baseline stereo","volume":"32","author":"Tola","year":"2010","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"10.3233\/ICA-230729_ref27","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1023\/B:VISI.0000027790.02288.f2","article-title":"Scale & affine invariant interest point detectors","volume":"60","author":"Mikolajczyk","year":"2004","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"10.3233\/ICA-230729_ref31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00138-021-01266-7","article-title":"UP-Net: Unique keyPoint description and detection net","volume":"33","author":"Yang","year":"2022","journal-title":"Machine Vision and Applications"},{"key":"10.3233\/ICA-230729_ref32","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.neucom.2021.07.030","article-title":"Learning local descriptors with multi-level feature aggregation and spatial context pyramid","volume":"461","author":"Liang","year":"2021","journal-title":"Neurocomputing"},{"issue":"1","key":"10.3233\/ICA-230729_ref36","doi-asserted-by":"crossref","first-page":"100096","DOI":"10.1016\/j.jnlest.2021.100096","article-title":"Image classification with superpixels and feature fusion method","volume":"19","author":"Yang","year":"2021","journal-title":"Journal of Electronic Science and Technology"},{"issue":"03","key":"10.3233\/ICA-230729_ref37","doi-asserted-by":"crossref","first-page":"2250007","DOI":"10.1142\/S0129065722500071","article-title":"Tiled sparse coding in eigenspaces for image classification","volume":"32","author":"Arco","year":"2022","journal-title":"International Journal of Neural Systems"},{"issue":"8","key":"10.3233\/ICA-230729_ref39","doi-asserted-by":"crossref","first-page":"2037","DOI":"10.1049\/ipr2.12466","article-title":"Image classification using convolutional neural network with wavelet domain inputs","volume":"16","author":"Wang","year":"2022","journal-title":"IET Image Processing"},{"key":"10.3233\/ICA-230729_ref41","doi-asserted-by":"crossref","first-page":"30","DOI":"10.2352\/issn.2168-3204.2022.19.1.7","article-title":"Enhanced computer vision using automated optimized neural network image pre-processing","volume":"19","author":"Fenton","year":"2022","journal-title":"Archiving Conference"},{"issue":"3","key":"10.3233\/ICA-230729_ref46","doi-asserted-by":"crossref","first-page":"A1867","DOI":"10.1137\/18M1168832","article-title":"Error analysis of zfp compression for floating-point data","volume":"41","author":"Diffenderfer","year":"2019","journal-title":"SIAM Journal on Scientific Computing"},{"issue":"9","key":"10.3233\/ICA-230729_ref48","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/2.410145","article-title":"Content based image retrieval systems","volume":"28","author":"Gudivada","year":"1995","journal-title":"Computer"},{"key":"10.3233\/ICA-230729_ref49","doi-asserted-by":"crossref","first-page":"108450","DOI":"10.1016\/j.compeleceng.2022.108450","article-title":"A comprehensive review of content-based image retrieval systems using deep learning and hand-crafted features in medical imaging: Research challenges and future directions","volume":"104","author":"Vishraj","year":"2022","journal-title":"Computers and Electrical Engineering"},{"issue":"4","key":"10.3233\/ICA-230729_ref50","doi-asserted-by":"crossref","first-page":"e0194526","DOI":"10.1371\/journal.pone.0194526","article-title":"An effective content-based image retrieval technique for image visuals representation based on the bag-of-visual-words model","volume":"13","author":"Jabeen","year":"2018","journal-title":"PloS one"},{"key":"10.3233\/ICA-230729_ref51","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.cviu.2016.10.008","article-title":"Efficient large-scale multi-class image classification by learning balanced trees","volume":"156","author":"Mai","year":"2017","journal-title":"Computer Vision and Image Understanding"},{"issue":"01","key":"10.3233\/ICA-230729_ref55","doi-asserted-by":"crossref","first-page":"2150042","DOI":"10.1142\/S0129065721500428","article-title":"Detection of trees on street-view images using a convolutional neural network","volume":"32","author":"Jodas","year":"2022","journal-title":"International Journal of Neural Systems"},{"issue":"12","key":"10.3233\/ICA-230729_ref56","doi-asserted-by":"crossref","first-page":"3074","DOI":"10.1109\/TNNLS.2017.2682102","article-title":"A new neural dynamic classification algorithm","volume":"28","author":"Rafiei","year":"2017","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"8","key":"10.3233\/ICA-230729_ref57","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1515\/revneuro-2020-0043","article-title":"Machine learning (ML) for the diagnosis of autism spectrum disorder (ASD) using brain imaging","volume":"31","author":"Nogay","year":"2020","journal-title":"Reviews in the Neurosciences"},{"issue":"6","key":"10.3233\/ICA-230729_ref58","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1159\/000512985","article-title":"Detection of epileptic seizure using pretrained deep convolutional neural network and transfer learning","volume":"83","author":"Nogay","year":"2021","journal-title":"European Neurology"},{"key":"10.3233\/ICA-230729_ref59","doi-asserted-by":"crossref","first-page":"104234","DOI":"10.1016\/j.bspc.2022.104234","article-title":"Diagnostic of autism spectrum disorder based on structural brain MRI images using, grid search optimization, and convolutional neural networks","volume":"79","author":"Nogay","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.3233\/ICA-230729_ref61","first-page":"1","article-title":"3D reconstruction based on hierarchical reinforcement learning with transferability","author":"Li","year":"2023","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"7","key":"10.3233\/ICA-230729_ref62","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1111\/mice.12930","article-title":"Building height calculation for an urban area based on street view images and deep learning","volume":"38","author":"Xu","year":"2023","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"10","key":"10.3233\/ICA-230729_ref63","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1111\/mice.12956","article-title":"Modeling adaptive platoon and reservation-based intersection control for connected and autonomous vehicles employing deep reinforcement learning","volume":"38","author":"Li","year":"2023","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"8","key":"10.3233\/ICA-230729_ref64","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1111\/mice.12931","article-title":"Effective pavement skid resistance measurement using multi-scale textures and deep fusion network","volume":"38","author":"Liu","year":"2023","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"issue":"6","key":"10.3233\/ICA-230729_ref65","doi-asserted-by":"crossref","first-page":"e12494","DOI":"10.1111\/exsy.12494","article-title":"A novel end-to-end deep learning scheme for classifying multi-class motor imagery electroencephalography signals","volume":"36","author":"Hassanpour","year":"2019","journal-title":"Expert Systems"},{"issue":"6","key":"10.3233\/ICA-230729_ref66","doi-asserted-by":"crossref","first-page":"e12647","DOI":"10.1111\/exsy.12647","article-title":"Deep learning techniques for recommender systems based on collaborative filtering","volume":"37","author":"Martins","year":"2020","journal-title":"Expert Systems"},{"key":"10.3233\/ICA-230729_ref67","first-page":"1","article-title":"Improvement of small objects detection in thermal images","author":"Chaverot","year":"2023","journal-title":"Integrated Computer-Aided Engineering"},{"issue":"2","key":"10.3233\/ICA-230729_ref68","doi-asserted-by":"crossref","first-page":"175","DOI":"10.3233\/ICA-210674","article-title":"Image binarization method for markers tracking in extreme light conditions","volume":"29","author":"\u0106urkovi\u0107","year":"2022","journal-title":"Integrated Computer-Aided Engineering"}],"container-title":["Integrated Computer-Aided Engineering"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/ICA-230729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:14:52Z","timestamp":1777454092000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/ICA-230729"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,26]]},"references-count":39,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/ica-230729","relation":{},"ISSN":["1069-2509","1875-8835"],"issn-type":[{"value":"1069-2509","type":"print"},{"value":"1875-8835","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,26]]}}}