Image Pattem Classification for Plant Disease Identification using Local Tri-directional Features

Aziz, Sumair; Bashir, Mudassar; Mughal, Ovais; Khan, Muhammad Umar; Khan, Arsalan

doi:10.1109/iemcon.2019.8936236

Cited by 16 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Purnamawati et al melaporkan hasil klasifikasi pada data daun padi menggunakan metode KNN dengan akurasi mencapai 87% [4], Huda et al dengan menggunakan metode yang sama pada data daun padi menghasilkan akurasi mencapai 93,3% [5]. Metode SVM digunakan oleh beberapa peneliti dalam klasifikasi penyakit daun, diantaranya Rumpf et al pada data daun bit gula dengan akurasi 86% [6], Anjna et al pada data daun cabai dengan akurasi 100% [7], Aziz et al pada data daun tomat dengan akurasi 94% [8] dan Rakhmawati et al pada data daun kentang dengan akurasi 80% [9]. Berdasarkan beberapa laporan dari penelitian sebelumnya, metode SVM telah berhasil melakukan identifikasi dan klasifikasi citra penyakit daun dengan akurasi yang optimal.…”

Section: Pendahuluanunclassified

“…Hasil pengujian juga menunjukkan perbedaan nilai akurasi dengan jumlah pembagian data, dimana jumlah data dengan pembagian 80:20 menghasilkan nilai akurasi sedikit lebih tinggi dibandingkan pembagian data 70:30 dan 60:40 secara berturut-turut (Gambar 4). Beberapa penelitian terkait deteksi dini dan klasifikasi penyakit daun tanaman sudah dilakukan, diantaranya klasifikasi daun padi [4], [5], klasifikasi daun bit gula [6], klasifikasi daun cabai [7], klasifikasi daun tomat [8], klasifikasi daun kentang [9] dan klasifikasi daun manggis [17]. Perbandingan hasil klasifikasi pada penelitian ini dan penelitian sebelumnya dapat dilihat pada tabel 2.…”

Section: Hasil Dan Pembahasanunclassified

See 1 more Smart Citation

Identifikasi dan Klasifikasi Penyakit Daun Jagung Menggunakan Support Vector Machine

Suhendra

Juliwardi²,

Sanusi³

2022

JTI

View full text Add to dashboard Cite

Tanaman jagung rentan terhadap serangan penyakit dimana penyakit ini dapat diketahui dari bercak yang terdapat pada daun. Penyakit daun tersebut dapat mengakibatkan turunnya kualitas dan kuantitas hasil panen. Tantangan utama dalam deteksi dini penyakit daun jagung secara manual yaitu ada banyak daun yang harus diidentifikasi dan terdapat perbedaan presepsi terhadap warna pada mata manusia berdasarkan kondisi visualnya.Tujuan dari penelitian ini adalah untuk melakukan deteksi dini dan klasifikasi penyakit daun jagung. Klasifikasi dilakukan melalui pendekatan metode Support Vector Machine (SVM) dengan memanfaatkan fitur warna dan fitur tekstur. Jumlah fitur yang digunakan yaitu 22 fitur yang terdiri dari 18 fitur warna dan 4 fitur tekstur. Data latih yang digunakan yaitu data sekunder yang diambil dari PlantVillage-Dataset dengan jumlah data sebanyak 3600 data. Eksperimen dilakukan dengan beberapa variasi fitur seperti hanya fitur warna, hanya fitur tekstur dan fitur gabungan warna dan tekstur dengan pembagian data 80:20, 70:30 dan 60:40. Pada setiap variasi fitur dan pembagian data lalu dihitung parameter evaluasi model. Hasil pengujian menunjukkan akurasi optimum sebesar 99,5% dengan fitur gabungan warna & tekstur

show abstract

Section: Pendahuluanunclassified

Section: Hasil Dan Pembahasanunclassified

Identifikasi dan Klasifikasi Penyakit Daun Jagung Menggunakan Support Vector Machine

Suhendra

Juliwardi²,

Sanusi³

2022

JTI

View full text Add to dashboard Cite

show abstract

“…A system proposed in which color co-occurrence method is utilized and extract texture attributes like Local Homogeneity Contrast, Energy, and Cluster Shade that help to calculate some statistical measures of diseased part [37]. The researchers proposed system for plant leaf diseases detection using Local Tri-directional Pattern for Features extraction that is used as variant of Local Binary Pattern (LBP) features descriptors and extracts discriminant information for each class, at the end three histograms are formed and serially fused to build final feature vector thus after classification the achieved accuracy is 94% [38]. The researchers proposed Artificial Neural Network (ANN) to specify Phalaenopsis seedling recognition.…”

Section: Features Extractionmentioning

confidence: 99%

“…Limitations and challenges: the focus should be on developing of the new advance algorithm for accurate and fast detection of leaves diseases [37]. The researcher proposed method for leaves disease detection but the proposed method work only for texture attribute so the color based features and shape feature along with texture features were remain un explored for the better performance [38]. The system proposed to find out Phalaenopsis seedling diseases but the researcher only focus on the find and classify the lesion area using CDD camera but not able to examine affected area on cover blades for growth observation [39].…”

Section: Features Extractionmentioning

confidence: 99%

Detection and Classification of Grain Crops and Legumes Disease: A Survey

Urva¹

2021

STAIQC

View full text Add to dashboard Cite

The agriculture plays very important role as it helps to accomplish the need of food among people. The production in agriculture consequentially contributes to the economy of every country. The grain crops rice, wheat, maize, and legumes are suffering a lot due to some viral, bacterial, and fungal diseases. The pest and variety of diseases can bring a heavy loss to the global economy. The monitoring of crops health and identification of diseases at early days is very challenging and emerging task in agriculture. So, it is very important to prevent crops from fatal diseases in the early stage, but the manual process of disease discovery can lead to erroneous magnitude of pesticides. The trouble is figure out by automate discovery of diseases and supplication of relevant medication on time. It is very necessary to find out accurate disease to overcome heavy loss to economy. From the few decades, to detect disease correctly, the process of detection become automate using emerging technologies and techniques using computer vision, machine learning and image processing. This article presents the extensive literature on existing methodologies utilized for recognition and classification of leaves diseases. The studies addresses that there is still many limitations and challenges find in different phases in plant disease detection system. The presented research also highlights the pros and cons of different techniques that help out the researchers for contribution in future.

show abstract

“…By comparison, local texture descriptors-based methods can provide high recognition accuracy and robustness to changes, but with low computational complexity. The local tridirectional pattern (LTriDP) is a simple but effective feature descriptor that was usually used for image retrieval [36][37][38] and image classification [39]. This paper extended the LTriDP for palmprint recognition.…”

Section: Introductionmentioning

confidence: 99%

Palmprint recognition based on the line feature local tri‐directional patterns

Wang

Liu

et al. 2022

IET Biometrics

View full text Add to dashboard Cite

Recent researches have shown that the texture descriptor local tri‐directional patterns (LTriDP) performs well in many recognition tasks. However, LTriDP cannot effectively describe the structure of palm lines, which results in poor palmprint recognition. To overcome this issue, this work proposes a modified version of LTriDP, called line feature local tri‐directional patterns (LFLTriDP), which takes into account the texture features of the palmprint. First, since palmprints contain rich lines, the line features of palmprint images, including orientation and magnitude, are extracted. The line features are more robust to variations compared to the original grayscale values. Then, the directional features are encoded as tri‐directional patterns. The tri‐directional patterns reflect the direction changes in the local area. Finally, the LFLTriDP features are constructed by the tri‐directional patterns, orientation and magnitude features. The LFLTriDP features effectively describe the structure of palm lines. Considering that most palm lines are curved, we use the concavity as supplementary information. The concavity of each pixel is obtained using the Banana filter and all pixels are grouped into two categories. The LFLTriDP features are refined to generate two feature vectors by the concavity to enhance the discriminability. The matching scores of the two feature vectors are weighted differently in the matching stage to reduce intra‐class distance and increase inter‐class distance. Experiments on PolyU, PolyU Multi‐spectral, Tongji, CASIA and IITD palmprint databases show that LFLTriDP achieves promising recognition performance.

show abstract

Image Pattem Classification for Plant Disease Identification using Local Tri-directional Features

Cited by 16 publications

References 28 publications

Identifikasi dan Klasifikasi Penyakit Daun Jagung Menggunakan Support Vector Machine

Identifikasi dan Klasifikasi Penyakit Daun Jagung Menggunakan Support Vector Machine

Detection and Classification of Grain Crops and Legumes Disease: A Survey

Palmprint recognition based on the line feature local tri‐directional patterns

Contact Info

Product

Resources

About