Abstract
Image sampling is one of the basic methods for image compression, which is efficient for image store, transmission, and applications. Existing sampling methods are designed for human-eye perception, which discard unconcerned information to decrease the amount of data considering the visual preference of human. However, these methods cannot adapt to the increasing machine vision tasks since there is a lot of redundant information for machine analysis to ensure the comfort of human eyes. In this paper, we propose an image sampling method for machine vision. We adopt a gray image to retain the main structural information of the image, and construct a concise color feature map based on the dominant channel of pixels to provide color information. Experiments on public datasets including COCO and ImageNet show that our sampling method can adapt to the characteristics of machine vision and greatly reduce the amount of data with little impact on the performance of mainstream computer vision algorithms.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Nyquist, H.: Certain topics in telegraph transmission theory. Proc. IEEE 90(2), 280–305 (1928)
Terzopoulos D., Vasilescu M.: Sampling and reconstruction with adaptive meshes. In Computer Vision and Pattern Recognition, pp. 70–75 (1991)
Eldar, Y., Lindenbaum, M., et al.: The farthest point strategy for progressive image sampling. IEEE Trans. Image Process. 6(9), 1305–1315 (1997)
Ramoni, G., Carrato, S.: An adaptive irregular sampling algorithm and its application to image coding. Image Vision Comput. 19(7), 451–460 (2001)
Wei, L., Wang, R.: Differential domain analysis for non-uniform sampling. ACM Trans. Graph. 30(4), 1–10 (2011)
Marvasti, F., Liu, C., Adams, G.: Analysis and recovery of multidimensional signals from irregular samples using nonlinear and iterative techniques. Sig. Process 36, 13–30 (1994)
Chen, W., Itoh, S., Shiki, J.: Irregular sampling theorems for wavelet subspace. IEEE Trans. Inf. Theory 44(3), 1131–1142 (1998)
Liu, Y.: Irregular sampling for spline wavelet. IEEE Trans. Inf. Theory 42(2), 623–627 (1996)
Oztireli, A., Alexa, M., Gross, M.: Spectral sampling of manifolds. AMC Trans. Grap. 29(6), 1–8 (2010)
Devir, Z., Lindenbaum, M.: Blind adaptive sampling of images. IEEE Trans. Image Process. 21(4), 1478–1487 (2012)
Sochen, N., Kimmel, R., Malladi, R.: A general framework for low level vision. IEEE Trans. Image Process. 7(3), 310–318 (1998)
Cheng, S., Dey, T., Ramos, E.: A manifold reconstruction from point samples. In: Proceedings of the Sixteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1018–1027 (2005)
Saucan, E., Appleboime, E., Zeevi, Y.: Geometric approach to sampling and communication. Sampl. Theory Sig. Image Process. 11, 1 (2010)
Vipula, S., Navin, R.: Data Compression using non-uniform sampling. In: International Conference on Signal Processing, pp. 603–607 (2007)
Ji, S., Xue, Y., Lawrence, C.: Bayesian compressive sensing. IEEE Trans. Sig. Process. 56(6), 2346–2356 (2008)
Bahzad, S., Nazanin, R.: Model-based nonuniform compressive sampling and recovery of natural images utilizing a wavelet-domain universal hidden Markov model. IEEE Trans. Sig. Process. 65(1), 95–104 (2017)
Matthew, M., Robert, N.: Near-optimal adaptive compressed sensing. IEEE Trans. Inf. Theory 60(7), 4001–4012 (2014)
Ali, T., Farokh, M.: Adaptive sparse image sampling and recovery. IEEE Trans. Comput. Imaging 4(3), 311–325 (2018)
Dai, Q., Henry, C., et al.: Adaptive image sampling using deep learning and its application on X-ray fluorescence image reconstruction. IEEE Trans. Multim. 22(10), 2564–2578 (2020)
William, P., Joan, M.: JPEG: Still image data compression standard. ISBN: 978–0442012724
Wang, Z., Li, F., Xu, J., Pamela, C.: Human-machine interaction oriented image coding for resource-constrained visual monitoring in IoT. IEEE Intern. Things J. (2022)
Mei, Y., Li, L., Li, Z., Li, F.: Learning-based scalable image compression with latent-feature reuse and prediction. IEEE Trans. Multim. 24, 4143–4157 (2022)
Jia, D., Wei, D., Li, F., et al.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)
Lin, T., Marie, M., et al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision, pp. 740–755 (2014)
Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Joseph, R., Santosh, D., Ross, G., Ali, F.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Joseph, R., Ali, F.: YOLO9000: better, faster, stronger. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6517–6525 (2017)
Joseph, R., Ali, F.: YOLOv3: An incremental improvement. https://arxiv.org/pdf/1804.02767.pdf
Glenn J., et al.: YOLOv5 homepage. https://github.com/ultralytics/yolov5
Ren, S., He, K., Ross, G., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Analysis Mach. Intell. 39(6), 1137–1149 (2017)
Zhou, X., Wang, D., Philipp, K.: Objects as points. https://arxiv.org/pdf/1904.07850.pdf
Mark, S., Andrew, H., et al.: MobileNetV2: inverted residuals and linear bottlenecks. https://arxiv.org/pdf/1801.04381.pdf
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representation, pp. 1–14 (2015)
Huang, G., Liu, Z., et al.: Densely connected convolutional networks. IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261–2269 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cui, J., Li, F., Wang, L. (2022). Image Sampling for Machine Vision. In: Fang, L., Povey, D., Zhai, G., Mei, T., Wang, R. (eds) Artificial Intelligence. CICAI 2022. Lecture Notes in Computer Science(), vol 13604. Springer, Cham. https://doi.org/10.1007/978-3-031-20497-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-20497-5_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20496-8
Online ISBN: 978-3-031-20497-5
eBook Packages: Computer ScienceComputer Science (R0)