DESIGNING AN AUTOMATED SYSTEM FOR PLANT LEAF RECOGNITION

The International journal of Multimedia & Its Applications, 2015

Because of huge diversity of plants existing on earth and large inter-species similarity, the manual process of identification of plants is difficult and at times, the results generated may be confusing. So, it is necessary to automate the process of identification of plants to generate faster and accurate results. Among various parts of plant, leaf is easily available in all seasons and can be easily scanned for understanding the shape details. So, in this paper, we have worked on plant identification using leaf image. In the process of identification of plants, the key challenge identified is to keep the size of feature vector reasonable and still achieve accurate and effective results. As the results are to be interpreted by the user, it was necessary to understand the theories behind human perception to reduce the semantic gap. We have designed and developed a tool 'SbLRS: Shape based Leaf Recognition System' which is a three-staged system that performs identification of plant using leaf shape. Our system can be helpful for following users-common layman person, as replacement for biologists in remote locations, as teaching aid for teachers and students, for a farmer to identify the plant species and to assist biologists in identification process. The parameters important for identifying leaf image according to human perception are identified and defined at three different levels. On the basis of results generated, the effectiveness of SbLRS is compared with existing contour based methods in terms of recall, precision. It was observed that our tool SbLRS showed satisfactory results for identification of plant using leaf at small feature vector size and simpler computations.

2015

Every leaf has its own identity and pocess some information that will help humans to identify and classify the plant by analyzing its leaves. The shape of leaf is a significant feature that most people use to recognise and classify a plant. It uses different parameters like diameter, physiological length, physiological width, leaf area and perimeter are basic geometry information can be extract from the leaf shape. The leaf identification is essential for scientists working in the agricultural and environmental fields. This work is a study of leaf identification and recognition system.The steps include the capturing the leaf image followed by a preprocessing. Later discussing about different classifiers and their accuracies

2015 International Conference on Pervasive Computing (ICPC), 2015

The last few decades have witnessed various approaches to automate the process of plant classification using the characteristics of the leaf. Several approaches have been proposed, and the majority focused on global shape features. However, one challenge that faces this task is the high interclass similarity amongst the leaves of different species in terms of the global shape. Furthermore, there always has been an obstacle against full automation as several approaches require user intervention to align the leaf. Therefore, a new set of Quartile Features (QF) is proposed in this paper to describe the partial shape of the leaf, in addition to an automated alignment approach to automate the system. The QF are extracted from the horizontal and vertical leaf quartiles to describe the partial shape of the leaf and the relations among its parts. The well-known Flavia dataset has been selected for the evaluation of the proposed system. The experimental results indicate the ability of the proposed alignment algorithm to align leaves with different shapes and maintain a correct classification accuracy regardless of the orientation of the input leaf samples. Furthermore, the proposed QF indicated promising results by increasing the accuracy of the classification by a range of approximately 26% to 30% when combined with Hu's Moment Invariants, using k-fold cross-validation technique.

2017

Plants are the most important living organisms on our planet because they are sources of energy and protect our planet against global warming. Botanists were the first scientist to design techniques for plant species recognition using leaves. Although many techniques for plant recognition using leaf images have been proposed in the literature, the precision and the quality of feature descriptors for shape, texture, and color remain the major challenges. This thesis investigates the precision of geometric shape features extraction and improved the determination of the Minimum Bounding Rectangle (MBR). The comparison of the proposed improved MBR determination method to Chaudhuri’s method is performed using Mean Absolute Error (MAE) generated by each method on each edge point of the MBR. On the top left point of the determined MBR, Chaudhuri’s method has the MAE value of 26.37 and the proposed method has the MAE value of 8.14. This thesis also investigates the use of the Convexity Meas...

Traitement du Signal, 2020

The main purpose of this research is to apply image processing for plant identification in agriculture. This application field has so far received less attention rather than the other image processing applications domains. This is called the plant identification system. In the plant identification system, the conventional technique is dealt with looking at the leaves and fruits of the plants. However, it does not take into account as a cost effective approach because of its time consumption. The image processing technique can lead to identify the specimens more quickly and classify them through a visual machine method. This paper proposes a methodology for identifying the plant leaf images through several items including GIST and Local Binary Pattern (LBP) features, three kinds of geometric features, as well as color moments, vein features, and texture features based on lacunarity. After completion of the processing phase, the features are normalized, and then Pbest-guide binary particle swarm optimization (PBPSO) is developed as a novel method for reduction of the features. In the next phase, these features are employed for classification of the plant species. Different machine learning classifiers are evaluated including k-nearest neighbor, decision tree, naï ve Bayes, and multi-SVM. We tested our proposed technique on Flavia and Folio leaf datasets. The final results demonstrated that the decision tree has the best performance. The results of the experiments reveal that the proposed algorithm shows the accuracy of 98.58% and 90.02% for the "Flavia" and "Folio" datasets, respectively.

2013

Plants are the backbone of all life on Earth and an essential resource for human well-being. Plant recognition is very important in agriculture for the management of plant species whereas botanists can use this application for medicinal purposes. Leaf of different plants have different characteristics which can be used to classify them. This paper presents a simple and computationally efficient method for plant identification using digital image processing and machine vision technology. The proposed approach consists of three phases: pre-processing, feature extraction and classification. Preprocessing is the technique of enhancing data images prior to computational processing. The feature extraction phase derives features based on color and shape of the leaf image. These features are used as inputs to the classifier for efficient classification and the results were tested and compared using Artificial Neural Network (ANN) and Euclidean (KNN) classifier. The network was trained with ...

2011

Shape is an important aspects in recognizing plants. Several approaches have been introduced to identify objects, including plants. Combination of geometric features such as aspect ratio, compactness, and dispersion, or moments such as moment invariants were usually used toidentify plants. In this research, a comparative experiment of 4 methods to identify plants using shape features was accomplished. Two approaches have never been used in plants identification yet, Zernike moments and Polar Fourier Transform (PFT), were incorporated. The experimental comparison was done on 52 kinds of plants with various shapes. The result, PFT gave best performance with 64% in accuracy and outperformed the other methods.