Avian egg classifier in android

By: Terdes, Nathaniel C
Publisher: Cebu City ; CIT-U ; 2013DDC classification: T T271 2013 Summary: Avian Egg Classifier classifies the type of eggs scanned by an Android system device using image processing, edge detection and color recognition. Currently, this project classifies the egg as either a duck egg or chicken egg. Future implementation hopes to achieve more classifications of avian eggs and accurate readings. Image processing was first used to filter and gather the needed data. Egg detection was then applied as to find a suitable target to classify. Hough circle was used to detect the top view of a circle. Egg size does not matter as there is no constant environment but the sample must not be too far or too near as to create a suitable or readable shape for the system to analyze. Also, good lighting conditions must be met in order for the device/application to identify the object clearly. The classification of the egg was based on the percentage of green generalized hues in a given egg detection. The samples were chosen and inspected visually that the eggs are not defective or spoiled to ensure correct sample output.
Tags from this library: No tags from this library for this title. Log in to add tags.
    Average rating: 0.0 (0 votes)
Item type Current location Home library Call number Status Date due Barcode Item holds
RESERVED BOOKS RESERVED BOOKS COLLEGE LIBRARY
COLLEGE LIBRARY
T T271 2013 (Browse shelf) Available T1722
Total holds: 0

Avian Egg Classifier classifies the type of eggs scanned by an Android system device using image processing, edge detection and color recognition. Currently, this project classifies the egg as either a duck egg or chicken egg. Future implementation hopes to achieve more classifications of avian eggs and accurate readings. Image processing was first used to filter and gather the needed data. Egg detection was then applied as to find a suitable target to classify. Hough circle was used to detect the top view of a circle. Egg size does not matter as there is no constant environment but the sample must not be too far or too near as to create a suitable or readable shape for the system to analyze. Also, good lighting conditions must be met in order for the device/application to identify the object clearly. The classification of the egg was based on the percentage of green generalized hues in a given egg detection. The samples were chosen and inspected visually that the eggs are not defective or spoiled to ensure correct sample output.

000-099

There are no comments for this item.

to post a comment.