计算机与现代化
計算機與現代化
계산궤여현대화
COMPUTER AND MODERNIZATION
2014年
1期
32-36
,共5页
BP神经网络%图像处理%分类%识别%字牌自动发牌机
BP神經網絡%圖像處理%分類%識彆%字牌自動髮牌機
BP신경망락%도상처리%분류%식별%자패자동발패궤
BP neural network%image processing%classification%recognition%automatically deal Chinese suit tiles machine
设计基于 BP神经网络的字牌识别系统，可用于实现字牌自动发牌机，以克服字牌比赛中人工洗牌的弊端。为提高系统的识别正确率，对字牌图像进行特定处理：（1）对图像像素数据通过闭运算、膨胀运算和腐蚀运算衍生出多种标准特征矩阵以增加训练样本，（2）挖掘图像特征数据规律提取颜色特征值和大小写特征值，组成特征向量并依此对图像进行分类编组，用特定编组的特征矩阵训练对应编组的BP神经网络。仿真结果表明，该系统识别正确率高，适应字牌比赛对自动发牌机的要求。
設計基于 BP神經網絡的字牌識彆繫統，可用于實現字牌自動髮牌機，以剋服字牌比賽中人工洗牌的弊耑。為提高繫統的識彆正確率，對字牌圖像進行特定處理：（1）對圖像像素數據通過閉運算、膨脹運算和腐蝕運算衍生齣多種標準特徵矩陣以增加訓練樣本，（2）挖掘圖像特徵數據規律提取顏色特徵值和大小寫特徵值，組成特徵嚮量併依此對圖像進行分類編組，用特定編組的特徵矩陣訓練對應編組的BP神經網絡。倣真結果錶明，該繫統識彆正確率高，適應字牌比賽對自動髮牌機的要求。
설계기우 BP신경망락적자패식별계통，가용우실현자패자동발패궤，이극복자패비새중인공세패적폐단。위제고계통적식별정학솔，대자패도상진행특정처리：（1）대도상상소수거통과폐운산、팽창운산화부식운산연생출다충표준특정구진이증가훈련양본，（2）알굴도상특정수거규률제취안색특정치화대소사특정치，조성특정향량병의차대도상진행분류편조，용특정편조적특정구진훈련대응편조적BP신경망락。방진결과표명，해계통식별정학솔고，괄응자패비새대자동발패궤적요구。
The Chinese suit tiles recognition system based on BPNN technology is designed to realize the automatically deal Chi -nese suit tiles machine to overcome a sort of drawbacks brought by artificial shuffle .In order to improve the accuracy of the recog-nition system, the training images are preprocessed:on the one hand, many kinds of standard features matrix are derived by the closing operation , dilation operation and erosion operation to increase the number of training samples , on the other hand , some regularities are found out and the color eigenvalues and the case eigenvalues are extracted , then the images and the BPNN are classified by these eigenvalues .The simulation results shows this technique is of high rate of classified accuracy and can meet the needs in the competition practical application of Chinese suit tiles .
