The classification of Fourier Transform Infrared spectra images is crucial in chemometrics. This paper proposes an efficient model based on deep learning approaches for enhancement and classification of the Fourier Transform Infrared Spectra (FTIR) images. The proposed model integrates three deep learning models including ResNet101, EfficientNetB0, and Wavelet Scattering transform (WST) to extract several features from FTIR.  Then the obtained features were fused in conjunction with standard statistical feature extraction. It followed by a subsequent classification phase that employs a Convolutional Neural Network (CNN) architecture, which demonstrates high accuracy in classifying the infrared spectra images into six different classes of ligands and their metal complexes. During the training phase, the network’s weights are iteratively updated using the Adam optimization algorithm. This model addresses the challenge of small and imbalanced datasets through an image oversampling process. Using random over-sampling technique, it enhances the training process and overall classification performance. The extracted features were analyzed using t-distributed Stochastic Neighbor Embedding (t-SNE) to visualize high-dimensional data in two dimensions. The results of the proposed model show high classification accuracy of 0.91%, low error rate of 0.08%, a sensitivity of 0.89% and a precision of 0.89%, false positive rate of 0.01%, F1 score of 0.89, Matthews Correlation Coefficient of 0.87 and Kappa of 0.68.

There are an urgent need of categorizing plant by its species, to help botanist setting up a plant species database. However, plant recognition model is still very challenging task in computer vision and can be onerous and time consuming because of inefficient representation approaches. This paper, proposes a recognition model for classifying botanical species from leaf images, using combination of variant-order statistics based measures. Hence, the spatial coordinates values of gray pixels defines the qualities of texture, for the proposed model a gray-scale approach is adopted  for analyzing the local patterns of leaves images using second and higher order statistical measures. While, first order statistical measures are used to extract color descriptors from leaves images. Evaluation of the proposed model shows the importance of combining variant-order statistics measures for enhancing the plant leaf recognition accuracy. Several experiments on Flavia dataset and swedish dataset are conducted. Experimental results indicates that; the proposed model yields to improve the recognition rate up to 97.1% and 94.7% for both Flavia and Swedish dataset respectively; while taking less execution time.