吉林大学学报(理学版)
吉林大學學報(理學版)
길림대학학보(이학판)
JOURNAL OF JILIN UNIVERSITY(SCIENCE EDITION)
2015年
1期
80-88
,共9页
表情合成%边缘提取%曲线拟合%极惯性矩
錶情閤成%邊緣提取%麯線擬閤%極慣性矩
표정합성%변연제취%곡선의합%겁관성구
expression synthesis%edge extraction%curve fitting%polar moment of inertia
先将人脸边缘图像分割为曲线段集,通过度量图像在曲线段两侧的局部纹理差异,形成特征序列。在此基础上,比较人脸样本集出现一类特定表情前后的图像,量化曲线段集和特征序列在此类表情运动作用下的变化,找出其中模式,从而在仅有某样本中性表情图像时,根据模式合成出样本在发生某类特定表情变化后的曲线段集和特征序列。运用该方法,可在初始样本有限的情况下,通过合成表情特征有效扩展样本空间,使识别算法更好地适应表情变化。
先將人臉邊緣圖像分割為麯線段集,通過度量圖像在麯線段兩側的跼部紋理差異,形成特徵序列。在此基礎上,比較人臉樣本集齣現一類特定錶情前後的圖像,量化麯線段集和特徵序列在此類錶情運動作用下的變化,找齣其中模式,從而在僅有某樣本中性錶情圖像時,根據模式閤成齣樣本在髮生某類特定錶情變化後的麯線段集和特徵序列。運用該方法,可在初始樣本有限的情況下,通過閤成錶情特徵有效擴展樣本空間,使識彆算法更好地適應錶情變化。
선장인검변연도상분할위곡선단집,통과도량도상재곡선단량측적국부문리차이,형성특정서렬。재차기출상,비교인검양본집출현일류특정표정전후적도상,양화곡선단집화특정서렬재차류표정운동작용하적변화,조출기중모식,종이재부유모양본중성표정도상시,근거모식합성출양본재발생모류특정표정변화후적곡선단집화특정서렬。운용해방법,가재초시양본유한적정황하,통과합성표정특정유효확전양본공간,사식별산법경호지괄응표정변화。
We proposed a new method to synthesize facial expression.First,we represented face binary edge map with curve segment group.The differences of local texture beside the curve segments were measured, which are considered as the features of the images. Then we measured the deformation of curve segments and the change of the features when the samples in the face database had some kind of expression change,and learned the pattern behind it.Even when we only have the neutral expression sample,following the pattern,we can still synthesize the curve segments and features of the sample for a certain type of expression change.Through this method,the sample space can be effectively extended,and a better performance is given by the recognition algorithm when it faces the challenge of multiple expression change.