Estimation of the marbled score in live beef cattle based on ICA and US texture information

基于 ICA 和 US 纹理信息估计活肉牛的大理石花纹分数

• 批准号: 23500238
• 负责人: FUKUDA OSAMU
• 金额: $ 3.08万
• 依托单位: National Institute of Advanced Industrial Science and Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2011
• 资助国家: 日本
• 起止时间: 2011 至 2013
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-23500238/
• 关键词: 超音波; パターン認識; 畜産; 独立成分分析; 超音波画像; テクスチャ

To accurately estimate the Beef Marbling Standard(BMS) number of live cattle using ultrasound echo imagings, we have developed a image recognition method by use of a neural network. We examine the efficiency of applying Independent Component Analysis(ICA) to the compression of multidimensional image features. We have implemented the estimation tests by use of ultrasound echo imagings measured from live cattles. The estimation accuracy was evaluated based on the cross validation method. The results confirmed that the correlation coefficient between the actual and the estimated values was higher by ICA (R=0.70, p<0.01) than by PCA (R=0.62, p<0.01). Also, we conducted the comparison experiments between the ICA based estimation and the estimation by an experienced inspector. The both methods examined the same ultrasound images. As a result, we confirmed that the proposed method had much the same capability as the experienced inspector to estimate BMS number.

为了准确估计牛肉大理石花纹标准（BMS）的活牛使用超声回波成像的数量，我们已经开发了一种图像识别方法，通过使用神经网络。我们研究的效率应用独立分量分析（伊卡）的多维图像特征的压缩。我们已经实现了估计测试，通过使用超声回波成像测量从活牛。基于交叉验证方法对估计精度进行了评价。结果表明，伊卡法的实际值与估计值的相关系数（R=0.70，p<0.01）高于PCA法（R=0.62，p<0.01）。此外，我们进行了比较实验之间的伊卡为基础的估计和估计的经验丰富的检查员。这两种方法检查相同的超声图像。因此，我们证实，所提出的方法具有相同的能力，有经验的检查员估计BMS数量。

项目成果

Estimation of Marbling Score in Live Cattle Based on Dynamic Ultrasound Image Using Neural Network

基于神经网络动态超声图像的活牛大理石花纹评分估计

• 发表时间: 2014
• 期刊: Proceedings of the 19th International Conference on Systems, Signals and Image Processing
• 作者: Fukuda;N. Nabeoka;T. Miyajima
• 通讯作者: T. Miyajima

独立成分分析と熟練専門技術者による肥育牛エコー画像のテクスチャ分類

通过独立成分分析和熟练的专业工程师对饲养场牛的回波图像进行纹理分类

• 发表时间: 2013
• 作者: Fukuda;N. Nabeoka;T. Miyajima;Takayuki Nakamura and Yuuichi Tashita;福田修，鍋岡奈津子，宮島
• 通讯作者: 福田修，鍋岡奈津子，宮島

Estimation of Marbling Score in Live Cattle Based on ICA and a Neural Network

基于 ICA 和神经网络的活牛大理石花纹评分估计

• 发表时间: 2013
• 期刊: Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics
• 作者: Fukuda;N. Nabeoka;T. Miyajima
• 通讯作者: T. Miyajima

Estimation of Marbling Score in Live Cattle based on Dynamic Ultrasound Image Using a Neural Network

使用神经网络基于动态超声图像估计活牛大理石花纹分数

• 发表时间: 2012
• 期刊: Proceedings of the 19th International Conference on Systems, Signals and Image Processing
• 作者: 中村 裕介;中村 恭之;43.O. FUKUDA，N. NABEOKA，T. MIYAJIMA
• 通讯作者: 43.O. FUKUDA，N. NABEOKA，T. MIYAJIMA

ニューラルネットを利用した超音波エコー画像のテクスチャ分類

使用神经网络对超声回波图像进行纹理分类

• 发表时间: 2012
• 作者: 姜有宣;長橋 宏;杉本晃宏;福田修
• 通讯作者: 福田修