Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
2 results
Search Results
Article Citation - WoS: 3Citation - Scopus: 3Texture Analysis of Polymer Modified Bitumen Images(Carl Hanser Verlag GmbH & Co. KG, 2011) Gümüştekin, Şevket; Topal, Ali; Şengöz, BurakThis study aims to analyze the textural features extracted from microscopic images of elastomeric and plastomeric type polymer modified bitumen (PMB) including five different types and contents of polymers. Fluorescence microscopy was used to capture microscopic images from thin films of PMB samples at different magnification scales (400×, 100×, and 40×). Gabor filters were utilized to extract the textural features of bitumen images. The features were used in three different query tests to quantify their representation capacity. The K nearest neighbor classifier was tested using leave-one-out cross validation. Textural analysis on the captured images provided numerical results that are in compliance with subjective visual tests. © 2011 Carl Hanser Verlag, Munich, Germany.Article Citation - WoS: 12Citation - Scopus: 19Quality Evaluation of Alaska Pollock (theragra Chalcogramma) Roe by Image Analysis. Part I: Weight Prediction(Taylor and Francis Ltd., 2012) Balaban, Murat Ömer; Chombeau, Melanie; Gümüş, Bahar; Cırban, DilşatRoe is an important product of the Alaska pollock (Theragra chalcogramma) industry. About 31% of the value for all pollock products comes from roe, yet roe is 5% of the weight of the fish. Currently, the size (weight), color, and maturity of the roe are subjectively evaluated. The objective of this study was to develop methods to predict the weight of Alaska pollock roe based on its view area from a camera and to differentiate between single and double roes. One hundred and forty-two pollock roes were picked from a processing line in a Kodiak, AK plant. Each roe was weighed, placed in a light box equipped with a digital video camera, images were taken at two different angles from one side, then turned over and presented at two different angles again (four images for each roe). A reference square of known surface area was placed by the roe. The following equations were used to fit the view area (X) versus weight (Y) data: linear, power, and second-order polynomial. Error rates for the classification of roes by weight decreased significantly when weight prediction equations for single and double roes were developed separately. A turn angle method, a box method, and a modified box method were tested to differentiate single and double roes by image analysis. Machine vision can accurately determine the weight of pollock roe. Practical Application Abstract: An image analysis method to accurately determine if pollock roe is a single or a double was developed. Then view area versus weight correlations were found for single and double roes that reduced incorrect weight classification rates to half that of human graders. © 2012 Copyright Taylor and Francis Group, LLC.