Abstract: The present disclosure relates to a user recognition method and a user recognition apparatus using a two-dimensional (2D) electromyogram (EMG) spectrogram image. The user recognition method using a 2D EMG spectrogram image may include (a) acquiring a one-dimensional EMG signal for a user, (b) converting the acquired one-dimensional EMG signal to a 2D EMG spectrogram image including a temporal feature and a frequency feature, and (c) recognizing the user based on the 2D EMG spectrogram image.

Abstract: Provided are a landmark-based ensemble network creation method for facial expression classification, and a facial expression classification method using a created ensemble network. More particularly, provided are a landmark-based ensemble network creation method and a facial expression classification method using a created ensemble network, wherein the ensemble network is created through an ensemble method on the basis of facial images and distance information between landmarks for each facial area extracted from the facial images, and facial expression classification is performed using the created ensemble network.

Abstract: The present disclosure relates to a user recognition method and a user recognition apparatus using a two-dimensional (2D) electromyogram (EMG) spectrogram image. The user recognition method using a 2D EMG spectrogram image may include (a) acquiring a one-dimensional EMG signal for a user, (b) converting the acquired one-dimensional EMG signal to a 2D EMG spectrogram image including a temporal feature and a frequency feature, and (c) recognizing the user based on the 2D EMG spectrogram image.

Abstract: The present disclosure relates to a method of normalizing a tachycardia electrocardiogram (ECG) on the basis of P-wave and T-wave data interpolation. The method of normalizing a tachycardia ECG on the basis of P-wave and T-wave data interpolation includes (a) receiving a first ECG signal from a subject, (b) detecting P-wave and T-wave peaks in the received first ECG signal, (c) segmenting the received first ECG signal into one-cycle ECG signals on the basis of the detected P-wave and T-wave peaks, (d) segmenting the one-cycle ECG signals into a P-wave period, a QRS complex period, and a T-wave period, and (e) normalizing the segmented P-wave and T-wave periods through data interpolation.

Abstract: The present disclosure relates to a method of normalizing a tachycardia electrocardiogram (ECG) on the basis of P-wave and T-wave data interpolation. The method of normalizing a tachycardia ECG on the basis of P-wave and T-wave data interpolation includes (a) receiving a first ECG signal from a subject, (b) detecting P-wave and T-wave peaks in the received first ECG signal, (c) segmenting the received first ECG signal into one-cycle ECG signals on the basis of the detected P-wave and T-wave peaks, (d) segmenting the one-cycle ECG signals into a P-wave period, a QRS complex period, and a T-wave period, and (e) normalizing the segmented P-wave and T-wave periods through data interpolation.

Abstract: An R wave peak detection method uses the periodicity of an electrocardiogram signal, in which expected R wave peaks are detected from an electrocardiogram signal, and a time difference between the expected R wave peaks that are detected is calculated in order to output, as actual R wave peaks, only expected R wave peaks that are greater than a threshold time difference, thereby avoiding a case in which the R wave peaks are erroneously detected from an non-ideal electrocardiogram signal.

Abstract: An R wave peak detection method uses the periodicity of an electrocardiogram signal, in which expected R wave peaks are detected from an electrocardiogram signal, and a time difference between the expected R wave peaks that are detected is calculated in order to output, as actual R wave peaks, only expected R wave peaks that are greater than a threshold time difference, thereby avoiding a case in which the R wave peaks are erroneously detected from an non-ideal electrocardiogram signal.

Abstract: Disclosed are a method for generating personal identification information using an electrocardiogram and a method for identifying a person using the personal identification information. The methods dramatically increase an identification rate by using two-dimensional image data converted from an electrocardiogram signal as personal identification information, and enable real-time identification by reducing a calculation amount by converting only a single electrocardiogram cycle into the two-dimensional image data.

Abstract: Disclosed are a method for generating an electrocardiogram for personal identification and a method for identifying a person using the electrocardiogram. The electrocardiogram generation method generates a normalized electrocardiogram by extracting single-cycle electrocardiogram signals meaningful for personal identification from an electrocardiogram of a person and by connecting the extracted single-cycle electrocardiogram signals arranged in temporal order. Therefore, the electrocardiogram generation method dramatically increases identification accuracy in personal identification.

Abstract: Disclosed are a method for generating an electrocardiogram for personal identification and a method for identifying a person using the electrocardiogram. The electrocardiogram generation method generates a normalized electrocardiogram by extracting single-cycle electrocardiogram signals meaningful for personal identification from an electrocardiogram of a person and by connecting the extracted single-cycle electrocardiogram signals arranged in temporal order. Therefore, the electrocardiogram generation method dramatically increases identification accuracy in personal identification.

Abstract: Disclosed are a method for generating personal identification information using an electrocardiogram and a method for identifying a person using the personal identification information. The methods dramatically increase an identification rate by using two-dimensional image data converted from an electrocardiogram signal as personal identification information, and enable real-time identification by reducing a calculation amount by converting only a single electrocardiogram cycle into the two-dimensional image data.

Abstract: A face feature extraction apparatus and method are provided. The face feature extraction apparatus for used in a two-dimensional (2D) face identification system includes: a local base vector generator generating a plurality of local base vectors to extract features of portions of a face from input 2D face image data of users; a local base vector selector selecting a predetermined number of local base vectors suitable for the face identification from the plurality of local base vectors generated by the local base vector generator; and a local base vector overlapper overlapping the local base vectors selected by the local base vector selector and generating a smaller number of overlapped local base vectors than the selected local base vectors. Thus, 2D face identification system having high face identification rate can be provided.

Abstract: A method and apparatus for classifying fingerprint image quality and a fingerprint image recognition system are provided. The method includes dividing a fingerprint image into a plurality of blocks, calculating and vectorizing quality classification parameters with respect to the respective blocks, obtaining quality classification values for the respective blocks by inputting the vectorized quality classification parameters into a trained quality classifier, and selecting a representative value of the quality classification values and determining the representative value as the quality of the fingerprint image. Since the quality of the fingerprint image can be accurately judged, reliability of the fingerprint image recognition system is increased.

Abstract: A fingerprint information storage apparatus includes a fingerprint information generating unit that extracts minutiae information from an authenticated user's fingerprint image and generates fingerprint information by inserting chaff minutiae information into the extracted minutiae information, a fingerprint information distributing unit that classifies the fingerprint information according to the extent that minutiae are distributed relative to the center of the fingerprint and distributively outputs the fingerprint information classified according to the distribution, and a first fingerprint information storage unit and a second fingerprint information storage unit that store the fingerprint information and distributively output according to the distribution, wherein the authenticated user's fingerprint information registered in the first fingerprint information storage unit is partially aligned and input fingerprint information is converted based on the information so that the converted input fingerprint i

Abstract: A face feature extraction apparatus and method are provided. The face feature extraction apparatus for used in a two-dimensional (2D) face identification system includes: a local base vector generator generating a plurality of local base vectors to extract features of portions of a face from input 2D face image data of users; a local base vector selector selecting a predetermined number of local base vectors suitable for the face identification from the plurality of local base vectors generated by the local base vector generator; and a local base vector overlapper overlapping the local base vectors selected by the local base vector selector and generating a smaller number of overlapped local base vectors than the selected local base vectors. Thus, 2D face identification system having high face identification rate can be provided.

Abstract: Provided are a fingerprint recognition apparatus and method which are capable of protecting registered fingerprint data and recognizing a fingerprint more quickly and accurately. In the fingerprint recognition apparatus, a fingerprint image generator generates fingerprint image data of an input fingerprint, and a memory stores registration fingerprint data for authentication. In a registration mode, a fingerprint recognition processor transforms the fingerprint image data into the irreversible registration fingerprint data using a specific transformation scheme, and stores the transformed registration fingerprint data. In an authentication mode, the fingerprint recognition processor transforms the fingerprint image data into comparison fingerprint data using the specific transformation scheme, compares whether the comparison fingerprint data is identical to the registration fingerprint data, and controls the authentication process according to the comparison result.

Abstract: Provided are a method and apparatus for identifying a fingerprint.

Abstract: In an apparatus for authenticating a user by employing feature points of a fingerprint image of the user, a fingerprint image input circuit scans a fingerprint of a user to be registered to provide a first fingerprint image and a fingerprint of a user to be authenticated to provide a second fingerprint image. A host provides registered feature points data corresponding to the first fingerprint image and target feature points data corresponding to the second fingerprint image. A security token circuit estimates a position difference and a direction difference between pairs of a registered feature point and a target feature point and corrects the two feature points based on the position difference and the direction difference to provide authentication result data.

Abstract: In an apparatus for authenticating a user by employing feature points of a fingerprint image of the user, a fingerprint image input circuit scans a fingerprint of a user to be registered to provide a first fingerprint image and a fingerprint of a user to be authenticated to provide a second fingerprint image. A host provides registered feature points data corresponding to the first fingerprint image and target feature points data corresponding to the second fingerprint image. A security token circuit estimates a position difference and a direction difference between pairs of a registered feature point and a target feature point and corrects the two feature points based on the position difference and the direction difference to provide authentication result data.