DCT and SVD Sparsity-Based Compressive Learning on Lettuces Classification
DOI:
https://doi.org/10.37385/jaets.v6i1.4506Keywords:
Compressive Learning, Accuracy, Discrete Cosine Transform, Singular Value Decomposition, Compressive SensingAbstract
Compressive Sensing (CS) technique in image compression represents efficient signal which offering solutions in image classification where the resources are constrained especially on a large image processing, storage resource, and computing performance. Compressive learning (CL) is a framework that integrates signal acquisition via compressed sensing (CS) and machine/deep learning for inference tasks directly on a small number of measurements, On the other hand, in real-world high-resolution (HR) data, where the image dataset is very limited CL, has the drawback of reduced accuracy under conditions of aggressive compression ratio. Here, a reconstruction method is necessary to maintain high levels of accuracy. To address this, we proposed a framework Deep Learning (DL) and Compressive Sensing that processing a small dataset of 92 images maintaining high accuracy. The framework developed in this paper employs processing sensing matrix A in compressive sensing with two transformation methods: DCT CL with Multi Neural Networks and the SVD method with GoogleNet framework. To maintain the same computation efficiency as DCT Compressive learning, SVD with GoogleNet framework provides a solution for object recognition, achieving accuracy values ranging from 89.47% to 63.15% for compression ratios of 3.97 to 31.75. This performance shows a linear tendency concerning the PSNR level, an index of signal reconstruction quality, and demonstrates an efficient process in the S matrix.
Downloads
References
Ahsan, M., Eshkabilov, S., Cemek, B., Küçüktopcu, E., Lee, C. W., & Simsek, H. (2021). Deep Learning Models to Determine Nutrient Concentration in Hydroponically Grown Lettuce Cultivars (Lactuca sativa L.). Sustainability, 14(1), 416. https://doi.org/10.3390/su14010416
Allwinnaldo, Budiman, G., Novamizanti, L., Alief, R. N., & Ansori, M. R. R. (2019). QIM-based Audio Watermarking using Polar-based Singular Value in DCT Domain. 2019 4th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), 216–221. https://doi.org/10.1109/ICITISEE48480.2019.9003921
Bartan, B., & Pilanci, M. (2021). Training Quantized Neural Networks to Global Optimality via Semidefinite Programming. http://arxiv.org/abs/2105.01420
Budiman, G., Suksmono, A. B., & Danudirdjo, D. (2020). Compressive Sampling with Multiple Bit Spread Spectrum-Based Data Hiding. Applied Sciences, 10(12), 4338. https://doi.org/10.3390/app10124338
Chen, J. I.-Z., & Pi, C.-S. (2022). Assessment for Different Neural Networks with FeatureSelection in Classification Issue. Sensors, 22(8), 3099. https://doi.org/10.3390/s22083099
Cui, Y., Wang, J., Qi, J., Zhang, Z., & Zhu, J. (2019). Underdetermined DOA Estimation of Wideband LFM Signals Based on Gridless Sparse Reconstruction in the FRF Domain. Sensors, 19(10), 2383. https://doi.org/10.3390/s19102383
Deng, W., Zhou, F., Gong, Z., Cui, Y., Liu, L., & Chi, Q. (2022). Disease Feature Recognition of Hydroponic Lettuce Images Based on Support Vector Machine. Traitement Du Signal, 39(2), 617–625. https://doi.org/10.18280/ts.390224
Dyah Irawati, I., Budiman, G., Saidah, S., Rahmadiani, S., & Latip, R. (2023). Block-based compressive sensing in deep learning using AlexNet for vegetable classification. PeerJ Computer Science, 9, e1551. https://doi.org/10.7717/peerj-cs.1551
Hamidon, M. H., & Ahamed, T. (2023). Detection of Defective Lettuce Seedlings Grown in an Indoor Environment under Different Lighting Conditions Using Deep Learning Algorithms. Sensors, 23(13), 5790. https://doi.org/10.3390/s23135790
Haq, E. U., Jianjun, H., Huarong, X., & Li, K. (2021). Block-based compressed sensing of MR images using multi-rate deep learning approach. Complex & Intelligent Systems, 7(5), 2437–2451. https://doi.org/10.1007/s40747-021-00426-6
Hua, J., Rao, J., Peng, Y., Liu, J., & Tang, J. (2022). Deep Compressive Sensing on ECG Signals with Modified Inception Block and LSTM. Entropy, 24(8), 1024. https://doi.org/10.3390/e24081024
Jo, Y., Chun, S. Y., & Choi, J. (2021). Rethinking Deep Image Prior for Denoising. http://arxiv.org/abs/2108.12841
K B, P., & J, M. (2020). Design and Evaluation of a Real-Time Face Recognition System using Convolutional Neural Networks. Procedia Computer Science, 171, 1651–1659. https://doi.org/10.1016/j.procs.2020.04.177
Lauguico, S. C., Concepcion II, R. S., Alejandrino, J. D., Tobias, R. R., Macasaet, D. D., & Dadios, E. P. (2020). A Comparative Analysis of Machine Learning Algorithms Modeled from Machine Vision-Based Lettuce Growth Stage Classification in Smart Aquaponics. International Journal of Environmental Science and Development, 11(9), 442–449. https://doi.org/10.18178/ijesd.2020.11.9.1288
Li, L., Xiao, S., & Zhao, Y. (2020). Image Compressive Sensing via Hybrid Nonlocal Sparsity Regularization. Sensors, 20(19), 5666. https://doi.org/10.3390/s20195666
Li, X., Feng, G., & Zhu, J. (2020). An Algorithm of l 1 -Norm and l 0 -Norm Regularization Algorithm for CT Image Reconstruction from Limited Projection. International Journal of Biomedical Imaging, 2020, 1–6. https://doi.org/10.1155/2020/8873865
Li, Z., Li, Y., Yang, Y., Guo, R., Yang, J., Yue, J., & Wang, Y. (2021). A high-precision detection method of hydroponic lettuce seedlings status based on improved Faster RCNN. Computers and Electronics in Agriculture, 182, 106054. https://doi.org/10.1016/j.compag.2021.106054
Liang, S., Bell, E., Qu, Q., Wang, R., & Ravishankar, S. (2024). Analysis of Deep Image Prior and Exploiting Self-Guidance for Image Reconstruction. http://arxiv.org/abs/2402.04097
Liu, J., Wang, Q.-G., & Yu, J. (2023). Convex Optimization-Based Adaptive Fuzzy Control for Uncertain Nonlinear Systems With Input Saturation Using Command Filtered Backstepping. IEEE Transactions on Fuzzy Systems, 31(6), 2086–2091. https://doi.org/10.1109/TFUZZ.2022.3216103
Machidon, A. L., & Pejovi?, V. (2023). Deep learning for compressive sensing: a ubiquitous systems perspective. Artificial Intelligence Review, 56(4), 3619–3658. https://doi.org/10.1007/s10462-022-10259-5
Mangia, M., Prono, L., Marchioni, A., Pareschi, F., Rovatti, R., & Setti, G. (2020). Deep Neural Oracles for Short-window Optimized Compressed Sensing of Biosignals. IEEE Transactions on Biomedical Circuits and Systems, 1–1. https://doi.org/10.1109/TBCAS.2020.2982824
Mou, C., & Zhang, J. (2022). TransCL: Transformer Makes Strong and Flexible Compressive Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–16. https://doi.org/10.1109/TPAMI.2022.3194001
Osorio, K., Puerto, A., Pedraza, C., Jamaica, D., & Rodríguez, L. (2020). A Deep Learning Approach for Weed Detection in Lettuce Crops Using Multispectral Images. AgriEngineering, 2(3), 471–488. https://doi.org/10.3390/agriengineering2030032
Pratondo, A., Ismail, Sujana, A. P., Susanti, F., Roedavan, R., & Budianto, A. (2023). Classification of Sweet Potato Leaf Variants using Transfer Learning. 2023 9th International Conference on Wireless and Telematics (ICWT), 1–6. https://doi.org/10.1109/ICWT58823.2023.10335271
Safitri, I., Suksmono, A. B., Danudirdjo, D., & Usman, K. (2023). Super-Resolution in Sparse Representation Fusion for Medical Images. 2023 International Conference on Electrical Engineering and Informatics (ICEEI), 1–6. https://doi.org/10.1109/ICEEI59426.2023.10346824
Satrya, G. B., Ramatryana, I. N. A., & Shin, S. Y. (2023). Compressive Sensing of Medical Images Based on HSV Color Space. Sensors, 23(5), 2616. https://doi.org/10.3390/s23052616
Sharif, M. S., Afolabi, M. O., Zorto, A., & Elmedany, W. (2022). Enhancement Techniques for Improving Facial Recognition Performance in Convolutional Neural Networks. 2022 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), 494–499. https://doi.org/10.1109/3ICT56508.2022.9990811
Shen, Q., Tian, J., & Pei, C. (2022). A Novel Reconstruction Algorithm with High Performance for Compressed Ultrafast Imaging. Sensors, 22(19), 7372. https://doi.org/10.3390/s22197372
Shen, Z., Chen, Q., & Yang, F. (2023). A convex relaxation framework consisting of a primal–dual alternative algorithm for solving ?0 sparsity-induced optimization problems with application to signal recovery based image restoration. Journal of Computational and Applied Mathematics, 421, 114878. https://doi.org/10.1016/j.cam.2022.114878
Singh, A., Rajan, P., & Bhavsar, A. (2020). SVD-based redundancy removal in 1-D CNNs for acoustic scene classification. Pattern Recognition Letters, 131, 383–389. https://doi.org/10.1016/j.patrec.2020.02.004
Song, Y., Cao, Z., Wu, K., Yan, Z., & Zhang, C. (2020). Learning Fast Approximations of Sparse Nonlinear Regression. http://arxiv.org/abs/2010.13490
Sultana, F., Sufian, A., & Dutta, P. (2019). A Review of Object Detection Models based on Convolutional Neural Network. https://doi.org/10.1007/978-981-15-4288-6_1
Tran, D. T., Gabbouj, M., & Iosifidis, A. (2022). Progressive and compressive learning. In Deep Learning for Robot Perception and Cognition (pp. 187–220). Elsevier. https://doi.org/10.1016/B978-0-32-385787-1.00014-2
Tran, D. T., Yamac, M., Degerli, A., Gabbouj, M., & Iosifidis, A. (2021). Multilinear Compressive Learning. IEEE Transactions on Neural Networks and Learning Systems, 32(4), 1512–1524. https://doi.org/10.1109/TNNLS.2020.2984831
Utami, N. S., Novamizanti, L., Saidah, S., & Apraz Ramatryana, I. N. (2021). SVD on a Robust Medical Image Watermarking based on SURF and DCT. 2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), 32–38. https://doi.org/10.1109/IAICT52856.2021.9532515
Wang, C., Li, Z., & Shi, J. (2019). Lightweight Image Super-Resolution with Adaptive Weighted Learning Network. http://arxiv.org/abs/1904.02358
Wang, S., Jiang, X., Liu, X., Dong, Z., Pei, R., & Wang, H. (2023). End-to-end reconstruction of multi-scale holograms based on CUE-NET. Optics Communications, 530, 129079. https://doi.org/10.1016/j.optcom.2022.129079
Wang, Yidong, Wu, M., & Shen, Y. (2024). Identifying the Growth Status of Hydroponic Lettuce Based on YOLO-EfficientNet. Plants, 13(3), 372. https://doi.org/10.3390/plants13030372
Wang, Yue, Xue, L., Yan, Y., & Wang, Z. (2023). A Novel Complex-Valued Gaussian Measurement Matrix for Image Compressed Sensing. Entropy, 25(9), 1248. https://doi.org/10.3390/e25091248
Wen, H., He, X., & Huang, T. (2022). Sparse signal reconstruction via recurrent neural networks with hyperbolic tangent function. Neural Networks, 153, 1–12. https://doi.org/10.1016/j.neunet.2022.05.022
Wu, W., & Pan, Y. (2022). Adaptive Modular Convolutional Neural Network for Image Recognition. Sensors, 22(15), 5488. https://doi.org/10.3390/s22155488
Xiao, D., Li, Y., & Li, M. (2023). Invertible Privacy-Preserving Adversarial Reconstruction for Image Compressed Sensing. Sensors, 23(7), 3575. https://doi.org/10.3390/s23073575
Yan, Y., Xu, X., Chen, W., & Peng, X. (2021). Lightweight Attended Multi-Scale Residual Network for Single Image Super-Resolution. IEEE Access, 9, 52202–52212. https://doi.org/10.1109/ACCESS.2021.3069775
Yao, H., Dai, F., Zhang, S., Zhang, Y., Tian, Q., & Xu, C. (2019). DR2-Net: Deep Residual Reconstruction Network for image compressive sensing. Neurocomputing, 359, 483–493. https://doi.org/10.1016/j.neucom.2019.05.006
Yu, J., Liu, K., Liu, W., Yao, W., & Xie, J. (2023). Recurrence plot image and GoogLeNet based historical abuse backtrace for li-ion batteries. Journal of Energy Storage, 74, 109378. https://doi.org/10.1016/j.est.2023.109378
Zeng, C., Wang, Z., Wang, Z., Yan, K., & Yu, Y. (2021). Image Compressed Sensing and Reconstruction of Multi-Scale Residual Network Combined with Channel Attention Mechanism. Journal of Physics: Conference Series, 2010(1), 012134. https://doi.org/10.1088/1742-6596/2010/1/012134