Leaf classification and identification using Canny Edge Detector and SVM classifier

Salman, Adil; Semwal, Ashish; Bhatt, Upendra; Thakkar, Vandana

doi:10.1109/icisc.2017.8068597

Cited by 31 publications

(18 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Up to now, researchers have proposed numerous effective methods for species recognition. Commonly used leaf recognition methods include PNN (Wu et al 2007), LDC (Kalyoncu and Toygar 2015), GBDT-PNN (Tang 2020), and SVM (Salman et al 2017;Ahmed and Hussein 2020). As seen in Table 5, the BP-RBF neural network achieved high performance in plant recognition systems using fewer samples and features.…”

Section: Discussionmentioning

confidence: 99%

Leaf recognition using BP-RBF hybrid neural network

Yang

et al. 2021

J. For. Res.

View full text Add to dashboard Cite

Plant recognition has great potential in forestry research and management. A new method combined back propagation neural network and radial basis function neural network to identify tree species using a few features and samples. The process was carried out in three steps: image pretreatment, feature extraction, and leaf recognition. In the image pretreatment processing, an image segmentation method based on hue, saturation and value color space and connected component labeling was presented, which can obtain the complete leaf image without veins and background. The BP-RBF hybrid neural network was used to test the influence of shape and texture on species recognition. The recognition accuracy of different classifiers was used to compare classification performance. The accuracy of the BP-RBF hybrid neural network using nine dimensional features was 96.2%, highest among all the classifiers.

show abstract

Section: Discussionmentioning

confidence: 99%

Leaf recognition using BP-RBF hybrid neural network

Yang

et al. 2021

J. For. Res.

View full text Add to dashboard Cite

show abstract

“…The adaptive threshold [73] was used to measure an image threshold in smaller areas, leading to different thresholds and better results in different light conditions for different regions of the same image. The image edges were then detected, utilizing canny edge detection [72] [110][111][112]. The procedure then required a method of expansion to reconcile a picture (A) with a kernel (B) that may be formed or scaled to add pixels to the herbal boundaries of a picture.…”

Section: B Image Pre-processingmentioning

confidence: 99%

Efficient and Automated Herbs Classification Approach Based on Shape and Texture Features using Deep Learning

Muneer

Fati

2020

IEEE Access

View full text Add to dashboard Cite

Recognizing the desired herb among thousands of herbs is an exhausting and time-consuming practice. Hence, herbs identification via a vision system is beneficial since the pharmacist and botanic need not to collect them through traditional ways. Thus, this paper proposed an efficient and automatic classification system to recognize Malaysian herbs that would be used in medical or cooking areas. As per the authors' knowledge, there is no evidence for similar studies on medical herbs in Malaysia. In the proposed system, we have investigated different classifiers to build an efficient classifier; then, the classifier was integrated with a mobile app to ease the real-time classification. The proposed system employed two classifiers, namely Support Vector Machine (SVM) and Deep Learning Neural Network (DLNN). The two models have been tested on our own dataset, which contains 1000 leaves. The experimental results showed that SVM achieved 74.63% recognition accuracy and DLNN achieved 93% recognition accuracy for both of the experimental model and the developed mobile app. Furthermore, the processing time was 4 seconds for SVM and 5 seconds for DLNN classifier, while the processing time using the mobile app was 2 seconds only.

show abstract

“…Dalam beberapa kasus, fitur warna dan bentuk telah digunakan untuk mendapatkan vektor fitur pada tahap klasifikasi [4], [7], [8]. Ada berbagai algoritma klasifikasi yang digunakan untuk mengklasifikasikan tanaman berdasarkan vektor fitur.…”

Section: Pendahuluanunclassified

Ekstrasi Fitur Daun Tembakau Berbasis Discrete Cosine Transform (DCT)

Nahari¹,

Editya²,

Alfita³

2020

JAIC Polibatam

View full text Add to dashboard Cite

Keberhasilan proses klasifikasi daun tembakau sangat bergantung pada ekstrasi fitur daun tembakau. Beberapa tahapan pengolahan citra digital dapat meningkatkan kemampuan dalam mengidentifikasi tembakau kualitas terbaik secara otomatis melalui ekstrasi fitur tekstur daun. Penelitian ini bertujuan untuk mengaplikasikan sistem ekstrasi fitur tekstur daun menggunakan metode Discrete Cosine Transform. Hasil Klasifikasi menjadi tolak ukur akurasi keberhasilan sistem dalam mengesktrasi fitur tekstur terbaik. Klasifikasi daun tembakau menuntut pengetahuan yang luas dan terminologi yang kompleks, bahkan grader profesional memerlukan waktu yang signifikan di bidang ini untuk penguasaan subjek. Hal ini disebabkan karena daun tembakau biasanya dianggap memiliki karakteristik yang berguna untuk identifikasi kualitas tembakau dimana ekstrasi fitur yang tepat melalui citra daun dapat dianggap sebagai masalah penelitian yang berperan penting untuk klasifikasi. Penelitian yang diusulkan bertujuan untuk menemukan model ekstrasi yang sesuai untuk mendapatkan fitur warna melalui konversi ruang warna YcbCr dan tekstur daun tembakau yang diperoleh dari transformasi ruang frekwensi Discrete Cosine Transform. Sedangkan untuk tahap klasifikasi menggunakan metode maximum likelihood. Hasil uji coba menunjukkan akurasi keberhasilan dalam pengklasifikasin daun tembakau sebesar 90 % melalui ekstrasi 12 fitur.

show abstract

Leaf classification and identification using Canny Edge Detector and SVM classifier

Cited by 31 publications

References 6 publications

Leaf recognition using BP-RBF hybrid neural network

Leaf recognition using BP-RBF hybrid neural network

Efficient and Automated Herbs Classification Approach Based on Shape and Texture Features using Deep Learning

Ekstrasi Fitur Daun Tembakau Berbasis Discrete Cosine Transform (DCT)

Contact Info

Product

Resources

About