The automatic and accurate identification of apoptosis facilitates large-scale cell analysis. Most identification approaches using nucleus fluorescence imaging are based on specific morphological parameters. However, these parameters cannot completely describe nuclear morphology, thus limiting the identification accuracy of models. This paper proposes a new feature extraction method to improve the performance of the model for apoptosis identification. The proposed method uses a histogram of oriented gradient (HOG) of high-frequency wavelet coefficients to extract internal and edge texture information. The HOG vectors are classified using support vector machine. The experimental results demonstrate that the proposed feature extraction method well performs apoptosis identification, attaining $95.7\%$ accuracy with low cost in terms of time. We confirmed that our method has potential applications to cell biology research.The automatic and accurate identification of apoptosis facilitates large-scale cell analysis. Most identification approaches using nucleus fluorescence imaging are based on specific morphological parameters. However, these parameters cannot completely describe nuclear morphology, thus limiting the identification accuracy of models. This paper proposes a new feature extraction method to improve the performance of the model for apoptosis identification. The proposed method uses a histogram of oriented gradient (HOG) of high-frequency wavelet coefficients to extract internal and edge texture information. The HOG vectors are classified using support vector machine. The experimental results demonstrate that the proposed feature extraction method well performs apoptosis identification, attaining $95.7\%$ accuracy with low cost in terms of time. We confirmed that our method has potential applications to cell biology research.