Automatic identification of butterfly species based on local binary patterns and artificial neural network

Kaya, Yılmaz; Kaycı, Lokman; Uyar, Murat

doi:10.1016/j.asoc.2014.11.046

Cited by 41 publications

(24 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Local binary patterns (LBP) [74] were considered as texture descriptors and they are applied in images analysis. Kaya et al [49] extracted five texture features: average, correlation, entropy and energy from the LBP matrix in their automated identification system for butterfly species. In the automated identification and classification system for algae [17], dissimilarity measurement, centroid distance spectrum, points of contours and some densitometry and morphological features like area, ferret diameters, extinction, centre of gravity coordinates, etc.…”

Section: Feature Extractionmentioning

confidence: 99%

“…Most of the classification methods are mentioned in [60,89,112], including structural, fuzzy, transform, neural network-based methods and many more. Some automated identification systems [55] employ neural networks or learning algorithms when there are many classes and small Automatic insect classification 10 SVM > 90 [56] Automated identification and retrieval of moth images 50 SRV 85 [25] Automatic identification of species 740 ANN 91-93 [35] Water monitoring -automated and real time identification and classification of algae 23 ANN: SOM 98 [17] Automatic identification of butterfly species 5 ANN 98 [49] Automated system for malaria parasite identification 2 SVM 80 [88] Automatic plant species identification 8 Sparse representation 76-79 [42] Automated identification of copepods 8 ANN 93.13 [55] Automated identification and retrieval of moth images 50 SRV attributes 34-70 [24] Automatic wild animal identification 26…”

Section: Classificationmentioning

confidence: 99%

See 1 more Smart Citation

How automated image analysis techniques help scientists in species identification and classification?

2018

View full text Add to dashboard Cite

Identification of taxonomy at a specific level is time consuming and reliant upon expert ecologists. Hence the demand for automated species identification incre-ased over the last two decades. Automation of data classification is primarily focussed on images while incorporating and analysing image data has recently become easier due to developments in computational technology. Research ef-forts on identification of species include specimens' image processing, extraction of identical features, followed by classifying them into correct categories. In this paper, we discuss recent automated species identification systems, mainly for categorising and evaluating their methods. We reviewed and compared different methods in step by step scheme of automated identification and classification systems of species images. The selection of methods is influenced by many variables such as level of classification, number of training data and complexity of images. The aim of writing this paper is to provide researchers and scientists an extensive background study on work related to automated species identification, focusing on pattern recognition techniques in building such systems for biodiversity studies. (Folia Morphol 2018; 77, 2: 179-193).

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

How automated image analysis techniques help scientists in species identification and classification?

2018

View full text Add to dashboard Cite

show abstract

“…The advantage of the proposed method is to provide better performance in the accuracy and complexity of other operators. Another field of imagery research is the detection of tuna based on textures and shapes using gray level co-occurrence matrix (GLCM) [2]. This method adds geometric feature extraction of the region of interest (ROI).…”

Section: Introductionmentioning

confidence: 99%

“…The results are shown in the merger between the GLCM and ROI methods to obtain an accuracy value of 86.67% [2]. Several methods and related research in the field of other images include the identification of butterfly species automatically using local binary pattern (LBP) method to detect the texture characteristics on the wing and then classified using the artificial neural network (ANN) [3].…”

Section: Introductionmentioning

confidence: 99%

Local Binary Pattern Method and Feature Shape Extraction for Detecting Butterfly Image

Kartika¹

2018

GEOMATE

View full text Add to dashboard Cite

ABSTRACT:Research in the field of information retrieval especially on image processing is proliferating. Various methods are developed to be able to detect images optimally and produce better accuracy. The process of image detection can use the dataset that exists around us. In this research, we use butterflies dataset, since the butterfly has unique colors, patterns, and diverse shapes. Therefore, we use local binary pattern method for texture feature extraction and region props for shape feature extraction. The results of each texture feature extraction and shape feature extraction will be a merging process. The results of the merging process get an accuracy of 66%. In addition, the system testing process with confusion matrix will produce 67.1% precision value, 66% recall and f-measure of 66.5%. The merging process of both methods shows the interplay of texture and shape extraction.

show abstract

“…Content-based image retrieval (CBIR) system uses features such as color, texture, shape, and spatial location for retrieving images. In CBIR, texture is the most significant feature and its classification has been used in various applications such as face recognition [1], fingerprint recognition [2], butterfly species identification [3], and dates fruit identification [4]. In previous studies, different approaches involving local binary pattern (LBP) [5], gray-level co-occurrence matrix [6], and wavelet transform [7] have been employed for texture feature extraction.…”

Section: Introductionmentioning

confidence: 99%

Local line directional neighborhood pattern for texture classification

Nithya¹,

Ramakrishnan²

2018

J Image Video Proc.

View full text Add to dashboard Cite

Local binary pattern (LBP) and combination of LBPs have shown to be a powerful and effective descriptor for texture analysis. In this paper, a novel approach to pattern recognition problem namely local line directional neighborhood pattern (LLDNP) for texture classification is proposed. The proposed LLDNP extracts the directional edge information of an image at 0°, 15°, 30°, 45°, 60°, 75°, 90°, 105°, 120°, 135°, 150°, and 165°. The sign and magnitude patterns are computed using the neighborhood pixel values in all directions. The sign pattern provides the local information of an image and is computed by comparing the neighborhood pixels. The magnitude pattern also provides additional information on images. The performance of the proposed method is compared with other existing methods by conducting experiments on five benchmark databases namely Brodatz, Outex, CUReT, UIUC, and Virus. The experimental results prove that the performance of the proposed method has achieved higher retrieval rate than other existing approaches.

show abstract

Automatic identification of butterfly species based on local binary patterns and artificial neural network

Cited by 41 publications

References 19 publications

How automated image analysis techniques help scientists in species identification and classification?

How automated image analysis techniques help scientists in species identification and classification?

Local Binary Pattern Method and Feature Shape Extraction for Detecting Butterfly Image

Local line directional neighborhood pattern for texture classification

Contact Info

Product

Resources

About