Face Gender Recognition Using Multi Layer Perceptron with OTSU Segmentation

Thepade, Sudeep D.; Abin, Deepa

doi:10.1109/iccubea.2018.8697480

Cited by 14 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At this stage, mobile application design is carried out, including implanting the perceptron method into a mobile application, the Perceptron method is used because it produces input -1, 0, 1, and one of the most famous prediction methods in artificial neural networks (ANN) [26], and has a high accuracy above 86% [27]. One method of having a high success rate in the recognition system is that Perceptron is proven by research conducted by Thepade in 2018 in recognizing face gender with successful rate reaches 99.658% [28], also Mishra in 2015 in detecting automatic extraction of water bodies from landsat imagery [29]. One of the factors that influence the success of the recognition system is the accuracy of selecting threshold values.…”

Section: Methodsmentioning

confidence: 99%

Detection of water quality in crayfish ponds with IoT

et al. 2021

View full text Add to dashboard Cite

Data from the Central Bureau of Statistics shows that during the first quarter of 2014 to 2019, the tendency of Indonesian crayfish export increases by an average of 3.54% in 2019 and reach 7.09 million USD. This number still fails to meet the global market demand caused by poor water quality due to cultivators’ lack of experience and education. Two parameters measured in water quality are temperature and pH. Thus, a device was made using IoT to maintain those conditions in order to increase the viability of the crayfish in the pond. The perceptron method is used to classify water quality based on those parameters. To send the data, ESP8266 is used as an intermediary for Arduino and cloud server. The result is that the information about the ponds’ condition can be seen via a smartphone. The method gives a value of 98.06% accurate in determining water quality.

show abstract

Section: Methodsmentioning

confidence: 99%

Detection of water quality in crayfish ponds with IoT

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The common methods are bimodal histogram threshold segmentation, the average gray level method, and the Otsu method. Thepade and Abin 11 applied Otsu segmentation to feature extraction from face images and achieved improved accuracy in face recognition. Liu et al 12 further improved Otsu's method by using multi-threshold segmentation to design an objective function.…”

Section: Maximum Interclass Variance Methods Of Image Binarymentioning

confidence: 99%

Spherical object recognition based on the number of contour edges extracted by fitting and convex hull processing

Zou

Qiu

2020

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

The detection of spherical targets in workpiece shape clustering and fruit classification tasks is challenging. Spherical targets produce low detection accuracy in complex fields, and single-feature processing cannot accurately recognize spheres. Therefore, a novel spherical descriptor (SD) for contour fitting and convex hull processing is proposed. The SD achieves image de-noising by combining flooding processing and morphological operations. The number of polygon-fitted edges is obtained by convex hull processing based on contour extraction and fitting, and two RGB images of the same group of objects are obtained from different directions. The two fitted edges of the same target object obtained at two RGB images are extracted to form a two-dimensional array. The target object is defined as a sphere if the two values of the array are greater than a custom threshold. The first classification result is obtained by an improved K-NN algorithm. Circle detection is then performed on the results using improved Hough circle detection. We abbreviate it as a new Hough transform sphere descriptor (HSD). Experiments demonstrate that recognition of spherical objects is obtained with 98.8% accuracy. Therefore, experimental results show that our method is compared with other latest methods, HSD has higher identification accuracy than other methods.

show abstract