Computer assisted plant identification system for Android

Abstract

Plant leaves provide sufficient features to distinguish them among other species. Identification of plants using leaf images is a classic problem in digital image processing. Usually those image processing systems use shape based digital morphological features for leaf identification task. Even there are number of studies on leaf based plant identification, very few of them are for mobiles. In this paper we describe a leaf image based plant identification system using SIFT features combining with Bag Of Word (BOW) model and Support Vector Machine (SVM) classifier. The system is trained to classify 20 species and obtained 96.48% accuracy level. Based on the results, we developed an Android application communicates with the server and gives users the ability to identify plant species using photographs taken of plant leaves using the smart phone.

Ayurvedic Medicinal Plants Identification: A Comparative Study on Feature Extraction Methods

“…Researchers have used Shape features, texture features, vein patterns for leaf recognition. The shape features used for plant leaf recognition are simple morphological shape descriptors [4][5][6], Hu Moments [7,8], SIFT descriptors [9][10][11], Histogram of Gradients (HOG) [12,13]. Texture features are used for plant leaf classification [14] and ayurvedic medicinal plant leaf recognition [15].…”

PhotoMetrix and colorimetric image analysis using smartphones

“…It is important to highlight that although there is a considerable amount of work that develops every procedure on the smartphone, many mobile applications are specific to certain samples or analytes, which does not make using these applications accessible. 100–115 …”

“…[91][92][93][94][95][96][97][98][99] It is important to highlight that although there is a considerable amount of work that develops every procedure on the smartphone, many mobile applications are specific to certain samples or analytes, which does not make using these applications accessible. [100][101][102][103][104][105][106][107][108][109][110][111][112][113][114][115] In this context, the PhotoMetrix ® application was developed in order to provide a free tool that can be used in various analysis, with different analytes and samples, as well as enabling univariate and multivariate analysis in the same application. The application was initially developed for the Android, IOS, and Windows operating systems; however, in its evolution, the focus was directed to the Android platform, as it is the most popular and easiest to maintain system.…”

Mobile application for the detection of black Sigatoka

“…Still, few apps currently serve as tools for improving agricultural processes. In [15], a mobile app was developed to classify 20 types of plants from images of leaves using SIFT and bag-of-words features. However, the system was limited to determining the type of plant and could not detect diseases in the sampled leaves.…”