“…This present study was conducted along the general automated insect process divided into three main steps: image preprocessing, feature extraction and recognition using dataset of butterfly in Order Lepidoptera as the research by [14] to classify in family level. The butterfly image dataset was obtained from Butterfly of America [20] and CSIRO ecosystem sciences -Australian moths online [21].…”
Section: Resultsmentioning
confidence: 99%
“…ELM with Radial basis function can give the highest recognition rate in Family Sphingidae at 98.89%. While SVM had better recognition rates for some families and the highest recognition rate of SVM in Family Sphingidae is 97.27% [14]. The recognition rates of ELM using sigmoid, triangular basis, sine, radial basis, hard limit function are 98.27%, 98.89%, 98.27%, 98.28%, 97.80%, respectively.…”
“…Thipayang et al was proposed part separating algorithm (PS) for feature extraction [14]. PS divides butterfly bodies into five features: head, front wing pair, back wing pair, abdomen, and symmetric half-body.…”
Section: Ps Feature Extractionmentioning
confidence: 99%
“…From the experiment in [13], the highest accuracy rate was 97.00% with the "Sine activation function". Lately, N. Thipayang et al proposed the Part Separating (PS) algorithm to extract features of butterfly and moth for the automated insect identification [14]. They divided the insect body into five main parts: head, front wing pair, back wing pair, abdomen, and symmetric half-body for family"s identification at order Lepidoptera.…”
Section: Introductionmentioning
confidence: 99%
“…Then, the extracted features are used as input features to SVM which its the highest accuracy was 97.27% at family Sphingidae only. However, their study [14] had some limitations, it means that usage of PS in SVM may not suitable for every family. We found that the approach can give high recognition rate for some family while accuracy rate of other family might drop dramatically.…”
Feature extraction and machine learning for classification plays an essential role in Automated Insect Identification (AII) because of its capability of insect classification in different taxonomic levels. Part Separating algorithm (PS) feature extraction integrated into Support Vector Machine (SVM) classifier could not demonstrate general results. The performance of SVM combined with PS was high only in Family Sphingdae of Order Lepidoptera but its accuracy rate may be dropped when used for classifying in other families. Therefore, this paper applied Extreme Learning Machine (ELM) having PS as the feature extraction process for AII for the butterfly family identification of Order Lepidoptera. In the pattern recognition process of image processing, the recognition ability of ELM classification with various activation functions and SVM were also investigated and compared. The experimental results showed that the classification in ELM using five insect features via the PS algorithm can be improved the as well as the ability to generalize every butterfly family of ELM performance, showing higher recognition rates than the SVM method in every family of order Lepidoptera.
“…This present study was conducted along the general automated insect process divided into three main steps: image preprocessing, feature extraction and recognition using dataset of butterfly in Order Lepidoptera as the research by [14] to classify in family level. The butterfly image dataset was obtained from Butterfly of America [20] and CSIRO ecosystem sciences -Australian moths online [21].…”
Section: Resultsmentioning
confidence: 99%
“…ELM with Radial basis function can give the highest recognition rate in Family Sphingidae at 98.89%. While SVM had better recognition rates for some families and the highest recognition rate of SVM in Family Sphingidae is 97.27% [14]. The recognition rates of ELM using sigmoid, triangular basis, sine, radial basis, hard limit function are 98.27%, 98.89%, 98.27%, 98.28%, 97.80%, respectively.…”
“…Thipayang et al was proposed part separating algorithm (PS) for feature extraction [14]. PS divides butterfly bodies into five features: head, front wing pair, back wing pair, abdomen, and symmetric half-body.…”
Section: Ps Feature Extractionmentioning
confidence: 99%
“…From the experiment in [13], the highest accuracy rate was 97.00% with the "Sine activation function". Lately, N. Thipayang et al proposed the Part Separating (PS) algorithm to extract features of butterfly and moth for the automated insect identification [14]. They divided the insect body into five main parts: head, front wing pair, back wing pair, abdomen, and symmetric half-body for family"s identification at order Lepidoptera.…”
Section: Introductionmentioning
confidence: 99%
“…Then, the extracted features are used as input features to SVM which its the highest accuracy was 97.27% at family Sphingidae only. However, their study [14] had some limitations, it means that usage of PS in SVM may not suitable for every family. We found that the approach can give high recognition rate for some family while accuracy rate of other family might drop dramatically.…”
Feature extraction and machine learning for classification plays an essential role in Automated Insect Identification (AII) because of its capability of insect classification in different taxonomic levels. Part Separating algorithm (PS) feature extraction integrated into Support Vector Machine (SVM) classifier could not demonstrate general results. The performance of SVM combined with PS was high only in Family Sphingdae of Order Lepidoptera but its accuracy rate may be dropped when used for classifying in other families. Therefore, this paper applied Extreme Learning Machine (ELM) having PS as the feature extraction process for AII for the butterfly family identification of Order Lepidoptera. In the pattern recognition process of image processing, the recognition ability of ELM classification with various activation functions and SVM were also investigated and compared. The experimental results showed that the classification in ELM using five insect features via the PS algorithm can be improved the as well as the ability to generalize every butterfly family of ELM performance, showing higher recognition rates than the SVM method in every family of order Lepidoptera.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.