Showing papers on "Thresholding published in 1990"

Performance study of several global thresholding techniques for segmentation

Abstract: A comparative performance study of five global thresholding algorithms for image segmentation was investigated. An image database with a wide variety of histogram distribution was constructed. The histogram distribution was changed by varying the object size and the mean difference between object and background. The performance of five algorithms was evaluated using the criterion functions such as the probability of error, shape, and uniformity measures Attempts also have been made to evaluate the performance of each algorithm on the noisy image. Computer simulation results reveal that most algorithms perform consistently well on images with a bimodal histogram. However, all algorithms break down for a certain ratio of population of object and background pixels in an image, which in practice may arise quite frequently. Also, our experiments show that the performances of the thresholding algorithms discussed in this paper are data-dependent. Some analysis is presented for each of the five algorithms based on the performance measures.

A direct method for fast three-dimensional serial reconstruction.

Abstract: A method for accurate three-dimensional reconstruction of openly connected porous structures is described The method is based on embedding of a specimen in a contrast coloured epoxy resin and serial sectioning in a standard hard tissue microtome A PC-based image processing system is used for direct digitization of the cut surface, and by thresholding two-phase images are obtained The process is fully automated, and about 170 sections can be produced, digitized, dichotomized, and stored per hour As an example of its applications, the method is used on trabecular bone, which is an anisotropic porous structure

A rule-based system for document image segmentation

Abstract: A rule-based system for automatically segmenting a document image into regions of text and nontext is presented. The initial stages of the system perform image enhancement functions such as adaptive thresholding, morphological processing, and skew detection and correction. The image segmentation process consists of smearing the original image via the run length smoothing algorithm, calculating the connected components locations and statistics, and filtering (segmenting) the image based on these statistics. The text regions can be converted (via an optical character reader) to a computer-searchable form, and the nontext regions can be extracted and preserved. The rule-based structure allows easy fine tuning of the algorithmic steps to produce robust rules, to incorporate additional tools (as they become available), and to handle special segmentation needs. >

Threshold superposition in morphological image analysis systems

Abstract: It is shown that four composite morphological systems, namely morphological edge detection, peak/valley extraction, skeletonization, and shape-size distributions obey a weak linear superposition, called threshold-linear superposition. The output image signal or measurement from each system is shown to be the sum of outputs due to input binary images that result from thresholding the input gray-level image at all levels. These results are generalized to a vector space formulation, e.g. to any finite linear combination of simple morphological systems. Thus many such systems processing gray-level images are reduced to corresponding binary image processing systems, which are easier to analyze and implement. >

Comments on Picture thresholding using an iterative selection method

Abstract: T.W. Ridler and E.S. Calvard (ibid., vol.SMC-8, p.630-2, Aug. 1978) presented a method of picture thresholding that was further mathematically developed by H.J. Trussel (ibid., vol.SMC-9, p.311, 1979). The principle of this method is to evaluate the unique threshold T for any image with a bimodal histogram. The present paper reinterprets the procedure as an algorithm designed to optimize the conversion of a multiple gray-level picture to a bimodel picture while maintaining as closely as possible the average luminance of the picture. >

Nonlinear operators for improving texture segmentation based on features extracted by spatial filtering

Abstract: An unsupervised texture segmentation system using texture features obtained from a combination of spatial filters and nonlinear operators is described. Local texture features are evaluated in parallel by a succession of four basic operations: (1) a convolution for local structure detection (local linear transform); (2) a first nonlinearity of the form f(x)= mod x mod /sup alpha /; (3) an iterative smoothing operator; and (4) a second nonlinearity g(x). The Karhunen-Loeve transform is used to reduce the dimensionality of the resulting feature vector, and segmentation is achieved by thresholding or clustering in feature space. The combination of nonlinearities f(x)= mod x mod /sup alpha / (in particular, alpha =2) and g(x)=log x maximizes texture discrimination, and results in a description with variances approximately constant for all feature components and texture regions. This latter property improves the performance of both feature reduction and clustering algorithms significantly. >

Transform coding using coefficient prediction techniques

Abstract: A system and method for improving the quality of decoded images, without any cost to compression efficiency, in both progressive still frame and motion video applications wherein the images are coded with intraframe transform based coding techniques, such as Discrete Cosine Transform (DCT) coding. Prediction of the AC components is utilized and operations are performed on the AC coefficient prediction in the decoder portions of the system in combination with a thresholding technique. Input images are subdivided into blocks of pixels, which are changed into blocks of coefficients by forward transform coding resulting in DC coefficients, representative of the average value in a block of pixels, and AC coefficients, representative of harmonic frequencies in a block of pixels. AC coefficient prediction is performed using both DC and AC coefficients from the block, whereupon the predicted coefficient values are thresholded and the thresholded coefficient values are added to their corresponding transform coefficient values for the given block. These steps are repeated for all of the blocks of the image and the image representation is recovered by applying an inverse transform operation to the results of all of the additions for all of the blocks of the image.

Image analysis for face modeling and facial image reconstruction

Abstract: We have studied a stereo-based approach to three-dimensional face modeling and facial image reconstruction virtually viewed from different angles. This paper describes the system, especially image analysis and facial shape feature extraction techniques using information about color and position of face and face components, and image histogram and line segment analysis. Using these techniques, the system can get the facial features precisely, automatically and independent of facial image size and face tilting. In our system, input images viewed from the front and side of the face are processed as follows: the input images axe first transformed into a set of color pictures with significant features. Regions are segmented by thresholding or slicing after analyzing the histograms of the pictures. Using knowledge about color and positions of the face, face and hair regions are obtained and facial boundaries extracted. Feature points along the obtained profile are extracted using information about curvature amplitude and sign, and knowledge about distance between the feature points. In the facial areas which include facial components, regions are again segmented by the same techniques with color information from each face component. The component regions are recognized using knowledge of facial component position. In each region, the pictures are filtered with various differential operators, which are selected according to each picture and region. Thinned images are obtained from the filtered images by various image processing and line segment analysis techniques. Then, feature points of the front and side views are extracted. Finally, the size and position differences and facial tilting between two input images are compensated for by matching the common feature points in the two views. Thus, the three-dimensional data of the feature points and the boundaries of the face are acquired. The two base face models, representing a typical Japanese man and woman, are prepared and the model of the same sex is modified with 3D data from the extracted feature points and boundaries in a linear manner. The images, which are virtually viewed from different angles, are reconstructed by mapping facial texture to the modified model.

A TV Camera System Which Extracts Feature Points For Non-Contact Eye Movement Detection

Abstract: This paper proposes a highly efficient camera system which extracts, irrespective of background, feature points such as the pupil, corneal reflection image and dot-marks pasted on a human face in order to detect human eye movement by image processing. Two eye movement detection methods are sugested: One utilizing face orientation as well as pupil position, The other utilizing pupil and corneal reflection images. A method of extracting these feature points using LEDs as illumination devices and a new TV camera system designed to record eye movement are proposed. Two kinds of infra-red LEDs are used. These LEDs are set up a short distance apart and emit polarized light of different wavelengths. One light source beams from near the optical axis of the lens and the other is some distance from the optical axis. The LEDs are operated in synchronization with the camera. The camera includes 3 CCD image pick-up sensors and a prism system with 2 boundary layers. Incident rays are separated into 2 wavelengths by the first boundary layer of the prism. One set of rays forms an image on CCD-3. The other set is split by the half-mirror layer of the prism and forms an image including the regularly reflected component by placing a polarizing filter in front of CCD-1 or another image not including the component by not placing a polarizing filter in front of CCD-2. Thus, three images with different reflection characteristics are obtained by three CCDs. Through the experiment, it is shown that two kinds of subtraction operations between the three images output from CCDs accentuate three kinds of feature points: the pupil and corneal reflection images and the dot-marks. Since the S/N ratio of the subtracted image is extremely high, the thresholding process is simple and allows reducting the intensity of the infra-red illumination. A high speed image processing apparatus using this camera system is decribed. Realtime processing of the subtraction, thresholding and gravity position calculation of the feature points is possible.

Adaptive thresholding technique

Abstract: ADAPTIVE THRESHOLDING TECHNIQUE ABSTRACT OF THE DISCLOSURE An adaptive thresholding technique is calculated by using a real-time 16 pixel running average (RA) 18 to which is added an offset value. The offset value 38 is the product of a programmable factor (alpha) and a Sum Absolute Difference (SAD) noise measurement. The adaptive threshold 42 is compared by a comparator 48 with a delayed analog video signal intensity value on line 46 for the pixel associated with the adaptive threshold. The comparator 48 provides a binary video output for further processing. A relative video output may also be provided by taking the difference of the analog video signal 46 and its corresponding running average 18.

Edge enhancement error diffusion thresholding for document images

Abstract: Apparatus for converting multilevel video images into a bilevel image having an accurate rendition of the original grayscale of the image. The apparatus performs enhanced preservation of edge information in the image when using error diffusion techniques.

The Opticom M-600™: A new LED automated perimeter

Abstract: The Opticom M-600TM is a new LED automated perimeter built and designed in Australia. The perimeter makes use of IBM compatible hardware, it may be interfaced with a practitioner's existing computer equipment and it is competitive in price with other perimeters. It has several worthy design features which make it an efficient and fast visual field tester, performing a screening of 100 points in a normal central 30o of visual field in three minutes per eye. A complete thresholding of the same area takes about 11 minutes per eye, both in the presence and absence of pathology. The efficiency of the thresholding algorithms results in severe losses of visual field being thresholded faster than most normal visual fields with milder losses taking marginally (five per cent) more time for thresholding than normal. The thresholding of the central visual field in pathological cases is achieved, on average, in 38 per cent less time with the Opticom M-600 than with the Humphrey Visual Field Analyser. We provide some data regarding normative values that can be adopted in the absence of a more formal study. Minor improvements for the presentation of data and statistical analysis of the results have been suggested.

Query learning based on boundary search and gradient computation of trained multilayer perceptrons

Abstract: A novel approach to query-based neural network learning is presented. A layered perceptron partially trained for binary classification is considered. The single-output neuron is trained to be either a 0 or a 1. A test decision is made by thresholding the output at, for example, 1/2. The set of inputs that produce an output of 1/2 forms the classification boundary. For each boundary point, the classification gradient can be generated. The gradient provides a useful measure of the sharpness of the multidimensional decision surfaces. Conjugate input pair locations are generated using the boundary point and gradient information and are presented to the oracle for proper classification. These new data are used to further refine the classification boundary, thereby increasing the classification accuracy. The result can be a significant reduction in the training set cardinality in comparison with, for example, randomly generated data points. An application example to power security assessment is given

Thresholding of gray level images using fractal dimensions.

Abstract: The locality of a two dimensional gray level image from which is generated a reference threshold value for converting the image to its corresponding binary image is determined by finding the fractal dimension of a hypothetical three dimensional surface overlying the two dimensional image.

Row-by-row segmentation and thresholding for optical character recognition

Abstract: During segmentation of individual characters in a column, the invention predicts for the next character an optimal minimum gray level sensitivity threshold while scanning pixel rows between characters by lowering the threshold unless or until noise in the image causes the scanner to detect too many "ON" pixels between adjacent numerals. During subsequent attempts to recognize the segmented character, the invention computes a confidence score and increases the sensitivity threshold above the predicted level if the confidence score is insufficient.

Statistical Edge Detection Operators for Linear Feature Extraction in SAR Images

Abstract: Edge detection in synthetic aperture radar (SAR) images is rendered difficult by the presence of speckle. The data are often filtered using adaptive filters independently of the edge detection process when, in fact, the two steps should be coupled (i.e., the local homogeneity criterion employed by an adaptive filter should be consistent with the edge detector criterion). Five different edge detection algorithms for SAR images are evaluated and compared. The detection algorithms are comprised of two operators based on non-parametric statistical tests, the Ratio of Averages test, difference of averages (essentially a gradient method), and a test based on the mean squared to variance ratio. Two edge thinning and thresholding operations are also compared: an algorithm proposed by Nevatia and Babu (1980), and one based on mathematical morphology (Serra, 1980). Initial testing is carried out on simulated imagery for accurate control of the signal being masked by speckle noise. We obtain the best results using t...

Method and apparatus for digital halftoning employing density distribution for selection of a threshold template

Abstract: Apparatus and method for converting digital, gray-level, image input data into binary valued halftone cells and preserving some of the sharpness information of the original data. The data is first converted to input halftone cells in which the pixel density gradient is analyzed to determine the density distribution within the cells. Depending upon the gradient, particular threshold value templates are selected to be used for thresholding the input data. Each template develops the output pixels beginning at different regions of the output halftone cell. The template for each input cell is selected which grows the binary pixels in the same region occupied by the densest pixels in the gray-level input data.

Segmentation based image coding using fractals and the human visual system

Abstract: A new segmentation-based image coding technique which performs segmentation based on roughness of textural regions and on properties of the human visual system (HVS) is presented. The image is segmented into texturally homogeneous region with respect to the degree of roughness as perceived by the HVS. The fractal dimension is used to measure the roughness of the textural regions. The segmentation is accomplished by thresholding the fractal dimension so that textural regions are classified into several classes. Three texture classes are chosen: perceived constant intensity, smooth texture, and rough texture. An image coding system with high compression and good image quality is achieved by developing an efficient coding technique for each texture class. >

Detecting and tracking low-observable targets using IR

Abstract: Detecting and Tracking Low—Observable Targets Using IRM. F. Fernandez, A. Aridgides, and D. BrayGE Advanced Technology LaboratoriesElectronics Parkway, Syracuse, N.Y. 13221ABSTRACTSensitivity to low—observable targets—-given a sequence of N frames of pre—processed(e.g., spatial/time-filtered) but unthresholded data—-may be enhanced by selecting,from among all possible paths traversing these frames, those containing anyindication that a target may be present. However, since only upper bounds regardingtarget velocities are usually known, explicit formulation of all feasible paths (andaccompanying confidence factors) becomes a formidable task even for small values ofN. In this paper we address this problem by utilizing a Dynamic Programming("Viterbi") algorithm to efficiently generate and evaluate, in an unthresholdedfashion, all possible paths through the N frames. Trajectories are tracedrecursively by assigning accumulated trajectory scores to each entry in a givenframe of data so as to maximize that entry's updated score. This Viterbi Track-Before—Detect procedure differs from standard Multiple Hypothesis Testing (MHT)methods in two ways. First, while in the MHT method the number of plausible pathsgrows exponentially (hence the need for introducing thresholds), in the Viterbiapproach they remain constant, equal to the number of data entries in a frame.Second, whereas in the MHT method trajectories are updated by selecting for eachexisting trajectory the best current (thresholded) detection, in the Viterbiapproach each current data value is updated with the best trajectory up to thatpoint. Simulation results show that application of the Viterbi Track-Before-Detectalgorithm over ten frames of IR data yields roughly a 7 dB improvement in detectionsensitivity over conventional thresholding/peak-detection procedures.1. BACKGROUNDOur philosophy in addressing the low-observable target detection problem (regardlessof the number of sensors being used) is that the closer the data processingfunctions can be brought to the sensor, the better the attainable performance. Inother words, the "detection" (or "threshold exceedence") decision should be avoidedor retarded because, quite simply, as soon as a thresholding function is invoked,information gets irretrievably lost. The low-observable detection/tracking problemthen becomes how to efficiently process the data so as to keep a manageable falsealarm rate and thus maintain a feasible computational load.For an infrared (IR) sensor, given a sequence of N frames of pre—processed (i.e.,clutter—filtered) but unthresholded data, sensitivity to low—observable targets maybe further enhancedThy selecting, from among all possible paths traversing theseframes, those containing any indiation that a target may be present. If thevelocity of the targets were known--and assuming that the filtered data has beensufficiently decorrelated between frames-—simple addition of the target strengthscould theoretically produce a Signal—to—Clutter ratio (SCR) gain of up to lOlogN dB.

A vision system for an automatic assembly machine of electronic components

Abstract: A vision system for the automatic assembly of electronic components is developed. The vision system presents information about positions, orientations, and quality of rectangular-shaped electronic components in real time. The orientation is detected by the windowed Hough transform along with a simple edge-detection method, whereas the position of each component is determined by using the projection method with dynamic thresholding. In addition, real-time implementation of the vision system in which multiple central processors are used for parallel processing of the algorithms is described. >

Adaptive error diffusion thresholding for document images

Abstract: Apparatus for converting multilevel video images into a bilevel image having an accurate rendition of the original grayscale of the image. The apparatus can provide an improved rendition of low contrast images.

Real-Time Focal-Plane Array Image Processor

Abstract: A focal-plane-array chip designed for real-time, general-purpose, image preprocessing is reported. A 48 X 48 pixel detector array and a 24 X 24 processing element processor array are monolithically integrated on the chip. The analog, charge-coupled device-based VLSI chip operates in the charge domain and has sensing, storing, and computing capabilities. It captures the image data and performs local neighborhood operations. The processor array is digitally programmable and uses a single-instruction, multiple-data parallel architecture. Various image preprocessing tasks such as level shifting, gain adjustment, thresholding, smoothing, sharpening, and edge detection can be implemented and A/D conversion can be performed prior to output. Frame-to-frame operations such as motion detection and tracking can be implemented as well. The chip was fabricated with a double-poly, double-metal process in a commercial CCD foundry. The prediction of the performance is based on numerical analysis and experimental results of testing a prototype charge-coupled computer. Operating at a modest clock frequency of 25 MHz, the chip is projected to achieve an internal throughput as high as 576 Mops with a 54 dB dynamic range (9-bit equivalent accuracy). The simulation of an edge detection algorithm implemented by the chip is presented. The power dissipation is estimated to be 20 mW and the total size of the 59-pad chip is 9.4 X 9.4 mm2.