A Neuronal Classification System for Plant Leaves Using Genetic Image Segmentation

Babatunde, Oluleye Hezekiah; Armstrong, Leisa; Leng, Jinsong; Diepeveen, Dean

doi:10.9734/bjmcs/2015/14611

Cited by 3 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1), the accuracy rate of the proposed system is less than the method in [12]. However, the accuracy rate of proposed method is greater than the methods in [3] and [11]. When compared to case (2), the accuracy rate of proposed system is less than the methods in [5] and [8].…”

Section: Resultsmentioning

confidence: 97%

See 1 more Smart Citation

Improving Leaf Classification Rate via Background Removal and ROI Extraction

Wu¹,

Tsai²,

Shih³

2016

JOIG

View full text Add to dashboard Cite

Modern description methods are used for plant classification through leaf recognition. These methods usually include color transformation, feature detection and description, dimension reduction, and classification. However, these methods use an original image as the input image from which to extract the features to be recognized. In this condition, computational complexity will increase. To reduce computational time, in the proposed method the Region of Interest (ROI) is extracted before extracting features from the image. Quality of image also plays an important role in increasing leaf classification rate. A good quality image gives better classification rate than noisy images. To extract features exactly from noisy images is very difficult which in-turn reduces leaf classification rate. To overcome problems occurring due to noisy image quality, background removal is done before extracting features from the image. That is, the proposed method includes color transformation, preprocessing (background removal and ROI extraction), feature extraction and description, and classification. In experiments and comparing results with and without preprocessing methods, the proposed method gives classification rate with an accuracy greater than 92.13% and the computational time in average is 133.94ms per leaf image. 

show abstract

Section: Resultsmentioning

confidence: 97%

“…Oluleye et al [11] combined a GA-based CNN edge detector and a RBF learning system for automatic classification of plant leaves. Their experimental results on the Flavia leaf dataset [3] show that their proposed method is more efficient than Canny, LoG, Prewitt, and Sobel edge detector in terms of speed and classification accuracy.…”

Section: Related Workmentioning

confidence: 99%