1. Input words were coded by a feature vector sequence.

2. With this method, texture feature vector cloud is generated backward after fuzzily processing descriptor of textures.

3. The establishment of fault feature vector is a precondition to fault diagnosis.

4. Using the subimage of an unknown target as feature vector and minimum distance rule for target recognition, experiments on simulated data are done.

5. A more stable feature vector with more information is extracted.

6. In first classification, the feature vector element fuzzy classification is used to class the characters. Recognizing system in detail makes use of peripheral direction contributivity feature.

6. is a sentence dictionary, on which you can find good sentences for a large number of words.

7. An image segmentation method based on the velocity feature vector of moving target was proposed.

8. In addition, a method for how to form feature vector is presented.

9. Images orthogonal transformation, including the Fourier, discrete cosine, Walsh, based on the feature vector, wavelet transform.

10. A multi-level document clustering algorithm was proposed based on association rules, It constructed document feature vector of topic and keyword by using a new method of document feature extraction.

11. The Short Time Fourier Transform (STFT) is utilized to estimate the power spectral density (PSD) of the tunneling-current signals and the data's feature vector was extracted in the frequency space.

12. Both analysis and experiments show that the recognition time is proportional to the square of the length of the feature vector, if dynamic time warping (DTW) algorithm is employed in recognition.

13. In this paper, from the natural characters of step edge of image, we proposed a feature vector that consists of 3 components based on the information measure accordingly.

14. Applied BP neural network to recognize numbers, and adopted a method of wipe off miscellaneous points to take out noise, and used a method of per pix feature extraction to extract feature vector.

15. Then the every frequency amplitude of auditory correlogram was coded as a feature vector expressing present frequency band characteristic.