Image Recognition from Deep Features using Implicit Split Logarithmic Loss-Based Optimized Random Forest
  IJCTT-book-cover
 		          
 
© 2023 by IJCTT Journal
Volume-71 Issue-7
Year of Publication : 2023
Authors : Abhinav Babbar, Pooja Gupta, Alok Gupta
DOI :  10.14445/22312803/IJCTT-V71I7P105

How to Cite?

Abhinav Babbar, Pooja Gupta, Alok Gupta, "Image Recognition from Deep Features using Implicit Split Logarithmic Loss-Based Optimized Random Forest," International Journal of Computer Trends and Technology, vol. 71, no. 7, pp. 29-43, 2023. Crossref, https://doi.org/10.14445/22312803/IJCTT-V71I7P105

Abstract
Image recognition collects meaningful data extracted from an image and performs various machine-based visual tasks. It is used in numerous applications such as self-driving cars, guiding autonomous robots, accident avoidance systems, and labeling the content of images with mega tags. It is considered a sub-category of digital technology that deals with regularities in image data, recognizing patterns, and then classifying them into categories by interpreting image pixel patterns. The traditional methods involved in image recognition perform sequential procedures like collecting, analyzing, and categorizing images manually, leading to time consumption and misclassification. So, ML algorithms such as instance-based, clustering, DT (Decision Tree), and others evolved to predict the images. But these methods involved over-fitting problems and uncertain outcome values leading to decreased accuracy. Hence the proposed system aims to improve the accuracy of predicting the images with suitable DL (Deep Learning) and ML (Machine Learning) based algorithms. The feature extraction is accomplished by implementing CNN (Convolutional Neural Network) algorithm. As CNN requires a large amount of training time and limited effectiveness for sequential data, an ORF (Optimised Random Forest) is employed. ISLLF (Implicit Split Log Loss Function) is used with ORF to predict the system's behaviour. The ISLLF is implemented during the training process and is used for optimizing classification models. The effectiveness of the respective model is calculated through F1-score, accuracy, recall, precision, confusion matrix, and ROC-AUC score. The proposed model is further compared with existing models to determine the proposed method's efficiency.

Keywords
Image recognition, Feature extraction, Deep Learning, Convolutional Neural Networks, Classification, Machine Learning, Random forest.

References

[1] Lushan Cheng, Xu Zhang, and Jie Shen, "Road Surface Condition Classification Using Deep Learning," Journal of Visual Communication and Image Representation, vol. 64, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Hao Fei et al., "Cotton Classification Method at the County Scale Based on Multi-Features and Random Forest Feature Selection Algorithm and Classifier," Remote Sensing, vol. 14, no. 4, p. 829, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Mohammadreza Sheykhmousa et al., "Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 6308-6325, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Xiaoxue Wang et al., "Land-Cover Classification of Coastal Wetlands Using the RF Algorithm for Worldview-2 and Landsat 8 Images," Remote Sensing, vol. 11, p. 1927, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Safa Riyadh Waheed et al., "CNN Deep Learning-Based Image to Vector Depiction," Multimedia Tools and Applications, vol. 82, pp. 20283-20302, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Ahmad Naeem et al., "Deep Learned Vectors' Formation Using Auto-Correlation, Scaling, and Derivations with CNN for Complex and Huge Image Retrieval," Complex & Intelligent Systems, vol. 9, pp. 1729-1751, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Khadija Kanwal et al., "Deep Learning Using Symmetry, Fast Scores, Shape-Based Filtering and Spatial Mapping Integrated with Cnn for Large Scale Image Retrieval," Symmetry, vol. 12, no. 4, p. 612, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] El houssaine Hssayni, Nour-Eddine Joudar, and Mohamed Ettaouil, “KRR-CNN: Kernels Redundancy Reduction in Convolutional Neural Networks,” Neural Computing and Applications, vol. 34, pp. 2443-2454, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Pankaj Mishra, Claudio Piciarelli, and Gian Luca Foresti, "A Neural Network for Image Anomaly Detection with Deep Pyramidal Representations and Dynamic Routing," International Journal of Neural Systems, vol. 30, no. 10, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] R. Sakthi Prabha, and M. Vadivel, "Brain Tumor Stages Prediction using FMS-DLNN Classifier and Automatic RPO-RG Segmentation," SSRG International Journal of Electrical and Electronics Engineering, vol. 10, no. 2, pp. 110-121, 2023.
[CrossRef] [Publisher Link]
[11] Xin Zhao et al., "3D-CNN-Based Feature Extraction of Ground-Based Cloud Images for Direct Normal Irradiance Prediction," Solar Energy, vol. 181, pp. 510-518, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Zixian Ge et al., “Hyperspectral Image Classification Method Based on 2D–3D CNN and Multibranch Feature Fusion,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 5776-5788, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Peng Wang, Xiaomin Zhang, and Yan Hao, "A Method Combining CNN and ELM for Feature Extraction and Classification of SAR Image," Journal of Sensors, vol. 2019, pp. 1-8, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Kai Huang et al., "A Lightweight Privacy-Preserving CNN Feature Extraction Framework For Mobile Sensing," IEEE Transactions on Dependable and Secure Computing, vol. 18, no. 3, pp. 1441-1455, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Yanchum Ma et al., "CNN-Feature Based Automatic Image Annotation Method," Multimedia Tools and Applications, vol. 78, pp. 3767-3780, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Yuanyuan Qing et al., "Deep and Wide Feature Based Extreme Learning Machine for Image Classification," Neurocomputing, vol. 412, pp. 426-436, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Nizar Ahmed et al., "Identification of Leukemia Subtypes from Microscopic Images Using Convolutional Neural Network," Diagnostics, vol. 9, p. 104, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Mohd Anul Haq, "Planetscope Nanosatellites Image Classification Using Machine Learning," Computer Systems Science and Engineering, vol. 42, no. 3, pp. 1031-1046, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Yongliang Qiao et al., "Individual Cattle Identification Using A Deep Learning Based Framework," IFAC-PapersOnLine, vol. 52, no. 30, pp. 318-323, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] G. Geetharamani and J. Arun Pandian, "Identification of Plant Leaf Diseases Using a Nine-Layer Deep Convolutional Neural Network," Computers & Electrical Engineering, vol. 76, pp. 323-338, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Sonia Mittal, and Sanskruti Patel, "Age Invariant Face Recognition Techniques: A survey on the Recent Developments, Challenges and Potential Future Directions," International Journal of Engineering Trends and Technology, vol. 71, no. 5, pp. 435-460, 2023.
[CrossRef] [Publisher Link]
[22] Yu-Dong Zhang et al., "Image-Based Fruit Category Classification by 13-Layer Deep Convolutional Neural Network and Data Augmentation," Multimedia Tools and Applications, vol. 78, pp. 3613-3632, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Salma Abdel Magid, Francesco Petrini, and Behnam Dezfouli, "Image classification on IoT Edge Devices: Profiling and Modeling," Cluster Computing, vol. 23, pp. 1025-1043, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Li Linhui, Jing Weipeng, and Wang Huihui, "Extracting the Forest Type from Remote Sensing Images by Random Forest," IEEE Sensors Journal, vol. 21, no. 16, pp. 17447-17454, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Jose Manuel Monsalve-Tellez, Jorge Luis Torres-León, and Yeison Alberto Garcés-Gómez, "Evaluation of SAR and Optical Image Fusion Methods in Oil Palm Crop Cover Classification Using the Random Forest Algorithm," Agriculture, vol. 12, no. 7, p. 955, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Xianyu Yu, Kaixiang Zhang, and Yanghui Zhang, "Land use Classification of Open-Pit Mine Based on Multi-Scale Segmentation and Random Forest Model," Plos one, vol. 17, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Xue Ji, Bisheng Yang, and Qiuhua Tang, "Seabed Sediment Classification Using Multibeam Backscatter Data Based on the Selecting Optimal Random Forest Model," Applied Acoustics, vol. 167, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Hu Gensheng et al., "Identification of Tea Leaf Diseases by Using an Improved Deep Convolutional Neural Network," Sustainable Computing: Informatics and Systems, vol. 24, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Yun Yang et al., "Two-Stage Selective Ensemble of CNN via Deep Tree Training for Medical Image Classification," IEEE Transactions on Cybernetics, vol. 52, pp. 9194-9207, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Ajala Sunday Adeyinka, "Convolutional Neural Network Implementation for Image Classification using CIFAR-10 Dataset," 2021.
[Google Scholar] [Publisher Link]
[31] Ali Abdullah Yahya et al., "A Novel Image Classification Method Based on Residual Network, Inception, and Proposed Activation Function," Sensors, vol. 23, no. 6, p. 2976, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Hironobu Fujiyoshi, Tsubasa Hirakawa, and Takayoshi Yamashita, “Deep Learning-Based Image Recognition for Autonomous Driving,” IATSS Research, vol. 43, no. 4, pp. 244-252, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Arnab Kumar Mishra et al., "Identifying COVID19 from Chest CT Images: A Deep Convolutional Neural Networks Based Approach," Journal of Healthcare Engineering, vol. 2020, 2020.
[CrossRef] [Google Scholar] [Publisher Link]