Sabiia Seb
PortuguêsEspañolEnglish
Embrapa
        Busca avançada

Botão Atualizar


Botão Atualizar

Registro completo
Provedor de dados:  OAK
País:  Japan
Título:  高精細枝肉横断面撮影装置からの画像を用いたBCSナンバーの推定
Prediction of BCS Number by Using Digital Images of Carcass Cross Sections Obtained from High-resolution Photographic Equipment
Autores:  高橋, 健一郎
堀, 武司
波, 通隆
本間, 稔規
小高, 仁重
口田, 圭吾
TAKAHASHI, Kenichiro
HORI, Takeshi
NAMI, Michitaka
HONMA, Toshinori
KOTAKA, Hitoshige
KUCHIDA, Keigo
Data:  2006-05
Ano:  2006
Palavras-chave:  Image analysis
Beef color standard
Japanese Black
Resumo:  高精細牛枝肉横断面撮影装置(以下,新型撮影装置)により得られた牛枝肉画像を複数の画像形式に変換し,BCSナンバーの推定に最適な方法を検討した.材料には新型撮影装置を用いて撮影された黒毛和種肥育牛46頭の第6-7肋骨間の鮮明な画像を用いた.画像はロース芯をその輪郭で抽出したJPEG形式とTIFF形式の画像,ロース芯の一部を矩形で切り取ったJPEG形式とTIFF形式の画像および輝度ムラを補正し,上記と同様の処理をしたJPEG画像(ロース芯,矩形)の計6種類の画像を用意した.その6種類の画像よりロース芯全体,ロース芯の筋肉および脂肪交雑部分のR(赤),G(緑),B(青)各階調値および輝度の平均値など,計108変数を算出した.格付員によるBCSナンバーを従属変数,画像解析で得られた形質を説明変数候補とする重回帰分析を行ったところ,輝度ムラ補正を行い,ロース芯をその輪郭で抽出した画像において決定係数がもっとも高かった(R2=0.793).推定されたBCSナンバーと格付員によるそれとの差が±0であったサンプルの割合は95.7%となった.以上のことから高精細撮影装置による圧縮画像からでも非常に高い精度でBCSナンバーを判定可能であることが示された. The purpose of this study was to examine a new method of predicting the BCS number by using digital images of carcass cross-sections obtained from high-resolution photographic equipment. Six types of digital images (JPEG and TIFF images along the outline of the rib eye,and JPEG and TIFF images for the rectangular area of the rib eye,and those JPEG images adjusted with the variation of luminance) of the cross section were taken for 46 Japanese Black steers using the new equipment. Average values of R (Red), G (Green),B (Blue) and the luminance for the whole rib eye,the muscle and the marbling area (total of 108 variables) were calculated. A multiple regression analysis was performed by the REG procedure in SAS to predict the BCS number. BCS numbers evaluated by graders were used as a dependent variable,and traits obtained by the image analysis were used as independent variables which were limited to 5. Images with adjusted luminance and extracted along the outline of the rib eye had the highest determination coefficient (R²=0.783). Ninety five point seven percent of the BCS numbers evaluated by graders were correctly predicted using BCS numbers by the image analysis,suggesting that it is possible to predict BCS numbers with high accuracy.
Idioma:  Japonês
Identificador:  http://ir.obihiro.ac.jp/dspace/handle/10322/937
Editor:  日本畜産学会
Formato:  application/pdf
Direitos:  日本畜産学会
Fechar
 

Empresa Brasileira de Pesquisa Agropecuária - Embrapa
Todos os direitos reservados, conforme Lei n° 9.610
Política de Privacidade
Área restrita

Embrapa
Parque Estação Biológica - PqEB s/n°
Brasília, DF - Brasil - CEP 70770-901
Fone: (61) 3448-4433 - Fax: (61) 3448-4890 / 3448-4891 SAC: https://www.embrapa.br/fale-conosco

Valid HTML 4.01 Transitional