Digital Image Classification for Malaysian Blooming Flower

Abstract

Digital image processing is a rapidly growing area of computer science since it was introduced and developed in the 1960's. In the case of flower classification, image processing is a crucial step for computer-aided plant species identification. Colour of the flower plays very important role in image classification since it gives additional information in terms of segmentation and recognition. On the other hand, Texture can be used to facilitate image-based retrieval system normally and it is encoded by a number of descriptors, which represented by a set of statistical measures such as gray-level co-occurrence matrix (GLCM) and Law's Order approach. This study addresses the application of NN and on image processing particularly for understanding flower image features. For predictive analysis, two techniques have been used namely, Neural Network (NN) and Logistic regression. The study shows that NN obtains the higher percentage of accuracy among two techniques. The MLP is trained by 1800 flower's dataset to classify 30 kinds of flower's type.

Machine Learning Models for Cultural Heritage Image Classification: Comparison Based on Attribute Selection

“…Moreover, the developed CNN model showed very good classification accuracy, confirming some of the findings from the literature. In particular, neural networks mostly perform better than other non-neural network algorithms used for classification tasks [26][27][28], especially when classifying images [29,30]. Furthermore, neural networks are more suitable for large sets of data due to the overfitting problems that can occur more often with small datasets.…”

Fusing well-crafted feature descriptors for efficient fine-grained classification

“…Most methods rely on contour analysis and SIFT features, which is robust but computationally inefficient. For larger datasets (30 to 79 species), accuracy vary from 63% to 94%, combining a variety of approaches such as HSV histograms, contour features, co-occurrence matrix (GLCM) for texture, RBF and probabilistic classification [10,11,12].…”

Application of Sparse Coded SIFT Features for Classification of Plant Images

“…A lot of research has been noticed in recent years in development of dictionary learning algorithms some of which are K-SVD of Aharon [38], Olshausen and field [18], SPAMS of Mairal [33] and others [34], [35], [36], [39]. Yang in 2011 proposed Fisher Discriminative Dictionary learning which instead of learning a common dictionary to all classes, learns a structured dictionary D as [D1, D2, D3… DC] where c is the number of classes hence increasing the discriminative power.…”

“…Yong Pei and Weiqun Cao provided the application of neural network for performing digital image processing for understanding the regional features based on shape of a flower [17]. Salahuddin et al proposed an efficient segmentation method which combines color clustering and domain knowledge for extracting flower regions from flower images [18]. D S Guru et al developed an algorithmic model for automatic flowers classification using KNN as the classifier [19].…”