This paper presents an original concept of computer systems construction for the automatic understanding of medical visual data based on cognitive analysis methods. This paper proposes a concept of a new IT image analysis systems, which is a significantly enhanced DSS-type system used in medical diagnosis support tasks. The essence of innovations introduced in this paper is in adding understandable medical data to the analysis process of the said data. Such a system is essentially different from all known DSS-type systems. In this paper we propose an acronym for the new system labelled UBIAS (understanding based image analysis systems). Cognitive methods, on which the UBIAS concept and construct are based, copy the psychological and neurophysiological processes of understanding the analysed data, as they take place in the brain of a competent and particularly gifted man.
{"title":"Cognitive Understanding Based Image Analysis Systems (UBIAS) of the Diagnostic Type","authors":"L. Ogiela","doi":"10.1109/IST.2007.379569","DOIUrl":"https://doi.org/10.1109/IST.2007.379569","url":null,"abstract":"This paper presents an original concept of computer systems construction for the automatic understanding of medical visual data based on cognitive analysis methods. This paper proposes a concept of a new IT image analysis systems, which is a significantly enhanced DSS-type system used in medical diagnosis support tasks. The essence of innovations introduced in this paper is in adding understandable medical data to the analysis process of the said data. Such a system is essentially different from all known DSS-type systems. In this paper we propose an acronym for the new system labelled UBIAS (understanding based image analysis systems). Cognitive methods, on which the UBIAS concept and construct are based, copy the psychological and neurophysiological processes of understanding the analysed data, as they take place in the brain of a competent and particularly gifted man.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130016503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Varian developed a portable 40 cm x 30 cm, active area, x-ray imager with 127 mum pixels. The imager is ruggedized i.e. can withstand drops from tabletop-to-hard surface, without breaking the imaging glass substrate or damaging the electronics inside. Moreover, it is rain water sealed for use in any open environment. The imager is powered from a rechargeable and replaceable battery, for more than 1 and 1/2 hours continuous use, or from line power (110 - 240 V AC). It also works from any car battery (12 -24 V DC) with a cigarette lighter adapter. Both the power line and the car battery adapter, charge the imager's internal battery. The imager has a Gigabit Ethernet Interface, which makes it easy to transfer and to view the x-ray images immediately on a laptop computer that can be a distance away, of up to 100 m. The imager can work in a cine or fluoroscopic mode at frame rates of up to 30 fr/s. It can also operate in radiographic or single shot mode. A special, Autorad mode has also been developed, where the imager is always on, but only starts transferring images (or catching a single image) when x-rays strike the imager.
{"title":"Development of a high resolution, portable x-ray imager for security applications","authors":"G. Zentai, L. Partain","doi":"10.1109/IST.2007.379590","DOIUrl":"https://doi.org/10.1109/IST.2007.379590","url":null,"abstract":"Varian developed a portable 40 cm x 30 cm, active area, x-ray imager with 127 mum pixels. The imager is ruggedized i.e. can withstand drops from tabletop-to-hard surface, without breaking the imaging glass substrate or damaging the electronics inside. Moreover, it is rain water sealed for use in any open environment. The imager is powered from a rechargeable and replaceable battery, for more than 1 and 1/2 hours continuous use, or from line power (110 - 240 V AC). It also works from any car battery (12 -24 V DC) with a cigarette lighter adapter. Both the power line and the car battery adapter, charge the imager's internal battery. The imager has a Gigabit Ethernet Interface, which makes it easy to transfer and to view the x-ray images immediately on a laptop computer that can be a distance away, of up to 100 m. The imager can work in a cine or fluoroscopic mode at frame rates of up to 30 fr/s. It can also operate in radiographic or single shot mode. A special, Autorad mode has also been developed, where the imager is always on, but only starts transferring images (or catching a single image) when x-rays strike the imager.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132906336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We develop a systems that detects and track individuals and groups of people in real-time, designed as a first screening of the iris-based access control. We use particle filtering in the conditional density propagation framework of hard and Blake, and base the face detection on the skin color in HSV colorspace. Particle assignment to faces is done automatically the use of X-Means algorithm. The X-means algorithm is modified to (1) avoid the local extrema (2) to deal better with odd number of clusters. The modified algorithm is fast enough to work in real time and outperforms its original version.
{"title":"Particle filters for multi-face detection and tracking with automatic clustering","authors":"L. Stasiak, A. Pacut","doi":"10.1109/IST.2007.379594","DOIUrl":"https://doi.org/10.1109/IST.2007.379594","url":null,"abstract":"We develop a systems that detects and track individuals and groups of people in real-time, designed as a first screening of the iris-based access control. We use particle filtering in the conditional density propagation framework of hard and Blake, and base the face detection on the skin color in HSV colorspace. Particle assignment to faces is done automatically the use of X-Means algorithm. The X-means algorithm is modified to (1) avoid the local extrema (2) to deal better with odd number of clusters. The modified algorithm is fast enough to work in real time and outperforms its original version.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132787229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper is dealing with steganography in DVD content. Classical steganography concerns itself on ways of embedding a secret message in a cover message such as a video stream or audio recording. The embedding is typically parameterized by a key. Without knowledge about this key, it is difficult for a third party to detect or remove the embedded material. Once sicret information was embedded in the cover object, this material is called a stego object [1], [2]. We embed a binary image in both video frames and audio tracks. This modification ensures higher payload and security.
{"title":"Transform domain steganography in DVD video and audio content","authors":"S. Badura, S. Rymaszewski","doi":"10.1109/IST.2007.379609","DOIUrl":"https://doi.org/10.1109/IST.2007.379609","url":null,"abstract":"This paper is dealing with steganography in DVD content. Classical steganography concerns itself on ways of embedding a secret message in a cover message such as a video stream or audio recording. The embedding is typically parameterized by a key. Without knowledge about this key, it is difficult for a third party to detect or remove the embedded material. Once sicret information was embedded in the cover object, this material is called a stego object [1], [2]. We embed a binary image in both video frames and audio tracks. This modification ensures higher payload and security.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"165 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133050977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A PC based measuring system which is used for analysing images from a simple CCD camera to provide information about motion parameters is presented in this work. The proposed approach has been developed for measuring small movements of micro robotic systems based on synthetic IPMC materials. The technique is based on processing the information from a fast analysis of subsequent images of the moving item. As the time of each frame in video recording is known, the software developed implements a graphic depiction of the movement (position or speed) in relation with time. The process uses a mechanism of localisation of the place of the interested item and has the capability for measurements of any movement with satisfactory accuracy. This method is particularly useful for monitoring movement of wings or arms in micro-robotics applications.
{"title":"Image Analysis for Measuring Motion Parameters with a CCD Camera","authors":"K. Tsiakmakis, T. Laopoulos","doi":"10.1109/IST.2007.379606","DOIUrl":"https://doi.org/10.1109/IST.2007.379606","url":null,"abstract":"A PC based measuring system which is used for analysing images from a simple CCD camera to provide information about motion parameters is presented in this work. The proposed approach has been developed for measuring small movements of micro robotic systems based on synthetic IPMC materials. The technique is based on processing the information from a fast analysis of subsequent images of the moving item. As the time of each frame in video recording is known, the software developed implements a graphic depiction of the movement (position or speed) in relation with time. The process uses a mechanism of localisation of the place of the interested item and has the capability for measurements of any movement with satisfactory accuracy. This method is particularly useful for monitoring movement of wings or arms in micro-robotics applications.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122005113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To generate volumetric underwater acoustic images a planar array of sensors is required to collect the signals coming from a 3-D scene. The method most frequently used to perform the spatial elaboration of the acquired signals is the beamforming algorithm. In general, owing to the huge number of sensors and the massive number of beam signals, computational load becomes prohibitive for real-time image generation. An efficient frequency beamforming implementation based on the use of the Chirp Zeta Transform (CZT) has been proposed in the literature for the case of a scene placed in the far-field and involving linear arrays. In this paper, we propose an algorithm to perform CZT beamforming on the wideband signals collected by a planar array and generated by a scene placed in the near-field. This extension becomes simpler and feasible thanks to (i) a non-conventional method of defining the azimuth and elevation angles; (ii) the Fresnel approximation in the delay computation; (iii) an adequate organization of the different operations. In terms of computational complexity, the analysis compares the solution developed with traditional beamforming techniques, showing several advantages of the proposed method.
{"title":"Digital Near Field Beamforming for Efficient 3-D Underwater Acoustic Image Generation","authors":"M. Palmese, A. Trucco","doi":"10.1109/IST.2007.379570","DOIUrl":"https://doi.org/10.1109/IST.2007.379570","url":null,"abstract":"To generate volumetric underwater acoustic images a planar array of sensors is required to collect the signals coming from a 3-D scene. The method most frequently used to perform the spatial elaboration of the acquired signals is the beamforming algorithm. In general, owing to the huge number of sensors and the massive number of beam signals, computational load becomes prohibitive for real-time image generation. An efficient frequency beamforming implementation based on the use of the Chirp Zeta Transform (CZT) has been proposed in the literature for the case of a scene placed in the far-field and involving linear arrays. In this paper, we propose an algorithm to perform CZT beamforming on the wideband signals collected by a planar array and generated by a scene placed in the near-field. This extension becomes simpler and feasible thanks to (i) a non-conventional method of defining the azimuth and elevation angles; (ii) the Fresnel approximation in the delay computation; (iii) an adequate organization of the different operations. In terms of computational complexity, the analysis compares the solution developed with traditional beamforming techniques, showing several advantages of the proposed method.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"756 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117007499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper reports on the implementation of a CMOS Photonic Mixer Device (PMD), which uses a new concept for demodulating photo-generated charges. The device uses a pair of PMOS transistors with an embedded photodiode to detect the intensity and phase of a modulated light signal. The charge demodulation, from photo-detector to the output, is accomplished exploiting the Charge Pumping phenomenon. Discovered in 1969, the Charge Pumping has been extensively used as a powerful analysis method for evaluate and quantify the degradation of MOS transistors. Experimental results, reported here, demonstrate that this phenomenon can also be employed as an alternative to the CCD charge transfer mechanism, which has been used for mixing photo-generated charges. The proposed PMD, compact and fully digitally controlled, is suitable to be organized in an array of pixels with embedded demodulating function.
{"title":"A Pixel-Embedded Charge-Pumping CMOS Photonic Mixer Device, Implementation and Perspectives","authors":"M. Gottardi, N. Massari","doi":"10.1109/IST.2007.379592","DOIUrl":"https://doi.org/10.1109/IST.2007.379592","url":null,"abstract":"This paper reports on the implementation of a CMOS Photonic Mixer Device (PMD), which uses a new concept for demodulating photo-generated charges. The device uses a pair of PMOS transistors with an embedded photodiode to detect the intensity and phase of a modulated light signal. The charge demodulation, from photo-detector to the output, is accomplished exploiting the Charge Pumping phenomenon. Discovered in 1969, the Charge Pumping has been extensively used as a powerful analysis method for evaluate and quantify the degradation of MOS transistors. Experimental results, reported here, demonstrate that this phenomenon can also be employed as an alternative to the CCD charge transfer mechanism, which has been used for mixing photo-generated charges. The proposed PMD, compact and fully digitally controlled, is suitable to be organized in an array of pixels with embedded demodulating function.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126450328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Handwriting is one of the most natural ways of writing characters. A pen tablet and a mouse are generally used as computer input devices. However, the feeling of writing is extremely different between the writing with the pen tablets or the mouse and the writing on the papers with the brush pen. We propose a new computer input device. A brush pen is a traditional writing material. The path of the brush pen is inputted to computers by using a CCD camera. At first, the inputted strokes are coded into histograms of the moving direction. The inputted characters are identified by the correlation values between the histograms of the inputted characters and the histograms of the reference pattern. Additionally, the line width of the strokes written by the brush pen is approximated by the straight lines. And marginal distributions of the approximated character for the horizontal distribution and for the vertical distribution are obtained. The result of comparison about the marginal distribution is used as subsidiary parameters for the character recognition. By using the proposed system, the natural hand writing characters can be inputted into the computer. And By using the two kinds of pattern recognition method, the improvement of the pattern recognition is achieved.
{"title":"Measurement of Strokes in Hand Writing Japanese Character","authors":"T. Sano, H. Ukida, H. Yamamoto","doi":"10.1109/IST.2007.379558","DOIUrl":"https://doi.org/10.1109/IST.2007.379558","url":null,"abstract":"Handwriting is one of the most natural ways of writing characters. A pen tablet and a mouse are generally used as computer input devices. However, the feeling of writing is extremely different between the writing with the pen tablets or the mouse and the writing on the papers with the brush pen. We propose a new computer input device. A brush pen is a traditional writing material. The path of the brush pen is inputted to computers by using a CCD camera. At first, the inputted strokes are coded into histograms of the moving direction. The inputted characters are identified by the correlation values between the histograms of the inputted characters and the histograms of the reference pattern. Additionally, the line width of the strokes written by the brush pen is approximated by the straight lines. And marginal distributions of the approximated character for the horizontal distribution and for the vertical distribution are obtained. The result of comparison about the marginal distribution is used as subsidiary parameters for the character recognition. By using the proposed system, the natural hand writing characters can be inputted into the computer. And By using the two kinds of pattern recognition method, the improvement of the pattern recognition is achieved.","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"236 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126624373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Donelli, M. Benedetti, P. Rocca, A. Massa, M. Pastorino
{"title":"IST 2007 Technical Program Tracks and Sessions","authors":"M. Donelli, M. Benedetti, P. Rocca, A. Massa, M. Pastorino","doi":"10.1109/ist.2007.379565","DOIUrl":"https://doi.org/10.1109/ist.2007.379565","url":null,"abstract":"","PeriodicalId":329519,"journal":{"name":"2007 IEEE International Workshop on Imaging Systems and Techniques","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121381791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：