Butterfly Image Classification Using Color Quantization Method on HSV Color Space and Local Binary Pattern

Kartika, Dhian Satria Yudha; Herumurti, Darlis; Yuniarti, Anny

doi:10.12962/j23546026.y2018i1.3512

Cited by 9 publications

(7 citation statements)

References 13 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Gradient-weighted Class Activation Mapping (Grad-CAM) [34] can provide visual explanations for classification decision. For the global feature map AC × H × W, and the gradient y s of the predicted score of the target category s, the weight w s t of the target category s corresponding to the t-th feature map A t (t ∈ [1, C]) can be calculated by Equation (7). After performing the ReLU operation on the weighted combination of the feature map, a Grad-CAM heatmap is obtained:…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Then, the texture feature extraction and shape feature are combined to classify the butterfly. DSY Kartika et al [7] propose to make use of the HSV (Hue, Saturation, Value) color space and local binary patterns (LBP) to extract color feature and texture feature, and combine these two features to classify butterflies. The authors of [8,9] adopted local binary pattern (LBP) and artificial neural network (ANN) to classify two and five types of butterflies, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fine-Grained Butterfly Classification in Ecological Images Using Squeeze-And-Excitation and Spatial Attention Modules

Xin

Chen

2020

Applied Sciences

View full text Add to dashboard Cite

Most butterfly larvae are agricultural pests and forest pests, but butterflies have important ornamental value and the ability to sense and respond to changes in the ecological environment. There are many types of butterflies, and the research on classification of butterfly species is of great significance in practical work such as environmental protection and control of agricultural and forest pests. Butterfly classification is a fine-grained image classification problem that is more difficult than generic image classification. Common butterfly photos are mostly specimen photos (indoor photos) and ecological photos (outdoor photos/natural images). At present, research on butterfly classification is more based on specimen photos. Compared with specimen photos, classification based on ecological photos is relatively difficult. This paper mainly takes ecological photos as the research object, and presents a new classification network that combines the dilated residual network, squeeze-and-excitation (SE) module, and spatial attention (SA) module. The SA module can make better use of the long-range dependencies in the images, while the SE module takes advantage of global information to enhance useful information features and suppress less useful features. The results show that the integrated model achieves higher recall, precision, accuracy, and f1-score than the state-of-the-art methods on the introduced butterfly dataset.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fine-Grained Butterfly Classification in Ecological Images Using Squeeze-And-Excitation and Spatial Attention Modules

Xin

Chen

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Beberapa penelitian mengenai machine learning dan image processing untuk pengolahan dataset kupukupu telah dilakukan oleh [1], [8]- [13]. Penelitian oleh Kartika et al (2018) ini menggunakan metode color feature extraction (color quantization+ HSV color space) dan metode texture feature (local binary pattern) untuk mengklasifikasi dataset kupu-kupu. Dataset yang digunakan adalah gambar kupu-kupu dengan resolusi 420x315 pixels berjumlah 890 images.…”

Section: Pendahuluanunclassified

“…Hasil klasifikasi dari penelitian ini mencapai akurasi sebesar 72% dengan precision value sebesar 76%, recall sebesar 72% dan f-measure sebesar 74%. [8] Penelitian oleh Kaya & Kayci (2014) menggunakan metode gray level co-occurrence matrix (GLCM) dan artificial neural networks (ANN) untuk melakukan klasifikasi gambar kupu-kupu. Dataset yang digunakan adalah gambar kupu-kupu dengan jumlah 140 butterfly images.…”

Section: Pendahuluanunclassified

Implementasi Model Arsitektur VGG16 dan MobileNetV2 Untuk Klasifikasi Citra Kupu-Kupu

Ramayanti¹,

Asri

Lionie

2022

JSAI

View full text Add to dashboard Cite

Untuk mengurangi populasi kupu-kupu, perlu adanya strategi untuk memantau jumlah dan spesies yang ada pada masing-masing ekosistem. Peran teknologi dapat membantu dalam proses ini, misalnya pengembangan sistem e-Butterfly untuk mengumpulkan gambar spesies kupu-kupu dari berbagai wilayah sehingga dapat diketahui jenis spesies yang masih ada dan letak wilayah hidupnya. Identifikasi spesies kupu-kupu dapat dilakukan dan dibantu oleh komputer dengan serangkaian proses lebih spesifik pada cabang ilmu machine learning dan image processing. Tujuan dari penelitian ini adalah untuk mengetahui kinerja (performance) dari model model arsitektur VGG16 dan MobileNetV2 untuk klasifikasi citra gambar kupu-kupu berdasarkan hasil ekstraksi fitur pada citra gambar tersebut. Dataset penelitian berisi 4955 gambar yang kemudian diberi label 50 butterfly species dengan ukuran 224 X 224 X 3. Akurasi terbaik diperoleh MobileNetV2 tanpa fine-tuning yaitu mencapai presentase 96%, dilanjutkan dengan VGG16 dengan fine-tuning, MobileNetV2 dengan fine-tuning, dan akurasi testing paling kecil diperoleh VGG16 tanpa fine-tuning. Untuk nilai precision, recall, F1-Score, dan Cohens Kappa lebih tinggi diperoleh model MobileNetV2 tanpa fine tuning, hal ini menunjukkan bahwa MobileNetV2 tanpa fine tuning lebih imbang dalam akurasi tiap kelasnya.

show abstract

“…HSV mempunyai representasi 3 karakteristik yaitu warna sebenarnya, kekuatan warna dan kecerahan warna dan Warna HSV diperoleh dengan melakukan konversi warna Red, Green, dan Blue [8]. Dalam hasil perhitungan representasi Hue dalam nilai skala [0-360], Saturation dan Value dalam nilai skala [0-1] [9].…”

Section: Metode Ekstraksi Ciri Hsvunclassified

Implementasi Metode K-Nearest Neighbor Untuk Pengenalan Buah Murbei Dengan Korelasi Kandungan Antosianin

Windana¹,

Handaratri

Zaen³

2021

JIRE

View full text Add to dashboard Cite

Abstract Mulberry fruit is a fruit that contains anthocyanins as antioxidants. This anthocyanin content can be obtained by chemically extracting it. However, knowing the content of anthocyanin without direct extraction requires other methods or methods. This method can take advantage of digital image processing for feature extraction of digital images of mulberry fruit. In this research, introduction a mulberry fruit test was carried out with the correlation of information on anthocyanin content with the KNN classification method. The feature extraction used was the HSV color and the LBP texture, each of feature looked for the mean, standard deviation, skewness and kurtosis. The results of the KNN test showed K = 3 the accuracy for the HSV feature is 53.3%, the LBP feature is 13.3% and the combination of HSV and LBP is 66.7%. Keywords : HSV, LBP, KNN, Mulberry Fruit, anthocyanins Abstrak Buah murbei merupakan buah yang mempunyai kandungan zat antosianin sebagai zat antioksidan. Kandungan antosianin ini bisa didapat dengan melakukan ekstrak secara kimiawi. Namun, lain halnya dalam mengetahui kandungan zat antosinain tanpa melakukan ekstraksi langsung membutuhkan cara atau metode lain. Metode tersbut dapat memanfaatkan digital image processing terhadap ekstraksi ciri citra digital buah murbei. Dalam penelitian ini dilakukan uji pengenalan buah murbei dengan korelasi informasi kandungan zat antosianin dengan metode klasifikasi KNN. Ektraksi ciri yang dimanfaatkan adalah warna HSV dan tekstur LBP yang mana masing-masing dicari nilai mean, standar deviasi, skewness dan kurtosis. Hasil pengujian KNN memperlihatkan K=3 akurasi untuk fitur HSV sebesar 53,3%, fitur LBP 13,3% dan kombinasi HSV dan LBP sebesar 66,7%. Kata kunci : HSV, LBP, KNN, Buah Murbei, Antosianin

show abstract

Butterfly Image Classification Using Color Quantization Method on HSV Color Space and Local Binary Pattern

Cited by 9 publications

References 13 publications

Fine-Grained Butterfly Classification in Ecological Images Using Squeeze-And-Excitation and Spatial Attention Modules

Fine-Grained Butterfly Classification in Ecological Images Using Squeeze-And-Excitation and Spatial Attention Modules

Implementasi Model Arsitektur VGG16 dan MobileNetV2 Untuk Klasifikasi Citra Kupu-Kupu

Implementasi Metode K-Nearest Neighbor Untuk Pengenalan Buah Murbei Dengan Korelasi Kandungan Antosianin

Contact Info

Product

Resources

About