nbis-wrapper-js 0.0.1

package/libnbis/nbis_x86-64_linux/man/man1/meancov.1

@@ -0,0 +1,92 @@
+.\" @(#)meancov.1 2008/10/02 NIST
+.\" I Image Group
+.\" G. T. Candela & Craig I. Watson
+.\"
+.TH MEANCOV 1B "02 October 2008" "NIST" "NBIS Reference Manual"
+.SH NAME
+meancov \- computes mean vector and covariance matrix for a set
+of feature vectors.
+.SH SYNOPSIS
+.B meancov
+.I <vecsfile_in[vecsfile_in...]> <meanfile_out> <meanfile_out_desc>
+.I <covfile_out> <covfile_out_desc> <ascii_outfiles> <message_freq>
+.SH DESCRIPTION
+.B Meancov
+computes sample mean vector and sample covariance matrix of a set of
+feature vectors.
+
+If several processors are available, it may be possible to save time,
+when computing the mean and covariance of a large set of feature vectors.
+First, run several simultaneous instances of meancov, each
+instance computing the mean and covariance of a subset of the vectors.
+Then, use cmbmcs to combine the resulting output files.  See the
+cmbmcs man page.
+.B Note:
+If using cmbmcs, the subset mean vectors made by the meancov instances
+must be saved for later use by cmbmcs even if, ultimately, all that
+is wanted is the overall covariance matrix. Construction of the
+overall covariance requires the subset means, as well as the
+subset covariances.
+.SH OPTIONS
+.TP
+.I <vecsfile_in[vecsfile_in...]>
+Input data file(s) in PCASYS "matrix" format, each consisting of a
+block of the vectors that are to be used, i.e. the vectors are the
+rows of the matrix (matrices).  Of course, all input matrices must
+have the same second dimension, which is the dimension of the
+constituent vectors. (Usually the output of \fBmkoas\fR.)
+.TP
+.I <meanfile_out>
+Mean file to be written, in PCASYS "matrix" format, with first dimension
+set to 1 and with second dimension set to the dimension of the input
+vectors.
+.TP
+.I <meanfile_out_desc>
+A string to be written into the mean output file as its description
+string.  This string can be of any length, but must not contain
+embedded newline characters.  If it contains spaces, tabs, or shell
+metacharacters that are not to be expanded, then it should be quoted.
+To leave the description empty, use '' (two single quotes, i.e.
+single\-quoted empty string).  To let meancov make a description
+(stating that this is a mean vector made by meancov and listing the
+names of the input files), use \- (hyphen).
+.TP
+.I <covfile_out>
+Covariance file to be written.  Meancov saves memory and cycles by
+allocating a buffer only large enough for the nonstrict lower triangle
+of the symmetric covariance matrix and computing only those elements,
+and it saves disk space by storing the covariance in PCASYS
+"covariance" format, which stores only the nonstrict lower triangle.
+The order of the covariance is the dimension of the input vectors.
+.TP
+.I <covfile_out_desc>
+Description string for covariance file or \- to let meancov make the
+description, same as for the mean file description argument.
+.TP
+.I <ascii_outfiles>
+If y, makes ascii output files; if n, binary.  Binary is recommended,
+unless the output files must be portable across different byte orders
+or floating\-point formats.
+.TP
+.I <message_freq>
+If a positive integer, then every this many vectors through each input
+file, during the accumulation phase, meancov writes a progress message
+to the standard output, and it also writes a few other progress
+messages.  If 0, no messages.
+.TP
+\fB-version
+\fRPrint ANSI/NIST stardand and NBIS software version.
+
+.SH EXAMPLE(S)
+.TP
+From \fItest/pcasys/execs/meancov/meancov.src\fR:
+.PP
+.RS
+.B % meancov ../../data/oas/fv[1-9].oas fv1-9.men - fv1-9.cov - n 100
+.br
+Compute the mean and covariance matrices for a set of feature vectors.
+.SH "SEE ALSO"
+cmbmcs (1B), mkoas (1B)
+
+.SH AUTHOR
+NIST/ITL/DIV894/Image Group

package/libnbis/nbis_x86-64_linux/man/man1/mindtct.1

@@ -0,0 +1,240 @@
+.\" @(#)mindtct.1 2008/10/02 NIST
+.\" I Image Group
+.\" Michael D. Garris
+.\"
+.TH MINDTCT 1C "02 October 2008" "NIST" "NBIS Reference Manual"
+.SH NAME
+mindtct \- detects minutiae from a fingerprint image that is either
+an ANSI/NIST 2007 formatted file or a WSQ compressed file.
+.SH SYNOPSIS
+.B mindtct
+.I [-b]
+.I [-m1]
+.I <finger_img_in>
+.I <oroot>
+.SH DESCRIPTION
+.B Mindtct
+takes either a WSQ compressed image file or parses a standard
+compliant ANSI/NIST-ITL 1-2007 file searching for the first
+occurrence of a grayscale fingerprint image record. The fingerprint
+image is processed and minutiae are automatically detected.
+
+If the input file was in ANSI/NIST 2007 format the minutiae results
+are formatted and stored using the NIST fields 5-12 in a Type-9 record.
+Upon successful completion, the input ANSI/NIST record sequence is
+augmented with two new records, the Type-9 minutiae record and a
+tagged field image record containing the results of image binarization.
+This augmented record sequence is then written to the output file
+<oroot>.mdt. The minutiae values are also written to a text file
+<oroot>.xyt in "x y theta quality" format. This <oroot>.xyt file
+is the format used by the bozorth3 matcher.
+
+If the input image is a WSQ compressed file the minutiae are only written
+to the text file <oroot>.xyt. In addition a file called <oroot>.brw
+is created which is a raw pixel file of the binarized image
+created by mindtct when detecting the minutiae points.
+
+The default is minutiae points computed based on the pixel origin being
+at the bottom left of the image and directions are pointing out and away
+from the ridge ending or bifurcation valley.
+
+.B Mindtct
+also generates the following text files in the current
+working directory: \fI<oroot>.dm\fR, \fI<oroot>.hcm\fR, \fI<oroot>.lcm\fR,
+\fI<oroot>.lfm\fR, \fI<oroot>.qm\fR, and \fI<oroot>.min\fR.
+These files are described below.
+
+.SH OPTIONS
+.TP
+.I [-b]
+perform image enhancement on low contrast images.  Only affects low
+contrast images, others are unchanged.
+.TP
+.I [-m1]
+write the minutiae points (in files <oroot>.{mdt,xyt,min}) according to
+ANSI INCITS 378-2004. This format has the pixel origin at the top left of the
+image and directions are pointing up the ridge ending or bifurcation valley.
+The default for \fBmindtct\fR has the pixel origin at the bottom left of
+the image and directions are pointing out and away from the ridge ending
+or bifurcation valley. NOTE: If this flag is used when extracting the
+mintuiae points it must also be used with the \fBbozorth3\fR matcher.
+
+.TP
+.I <finger_img_in> 
+the fingerprint file to be processed
+.TP
+.I <oroot>
+the root name for the output files (<oroot>.???)
+.TP
+\fB-version
+\fRPrint ANSI/NIST stardand and NBIS software version.
+
+.SH TEXT OUTPUT FILES
+.TP
+.I <oroot>.dm
+The \fIDirection Map\fR represents the direction of ridge flow within
+the fingerprint image.  The map contains a grid of integer directions,
+where each cell in the grid represents an 8x8 pixel neighborhood
+in the image.  Ridge flow angles are quantized into 16 integer
+bi-directional units equally spaced on a semicircle.  Starting with
+vertical direction 0, direction units increase clockwise and
+represent incremental jumps of 11.25 degrees, stopping at direction
+15 which is 11.25 degrees shy of vertical.  Using this scheme, direction
+8 is horizontal.  A value of -1 in this map represents a neighborhood
+where no valid ridge flow was determined.
+.TP
+.I <oroot>.hcm
+The \fIHigh-Curvature Map\fR represents areas in the image having
+high-curvature ridge flow.  This is especially true of core and delta
+regions in the fingerprint image, but high-curvature is not limited
+to just these cases.  This is a bi-level map with same dimension as
+the Direction Map.  Cell values of 1 represent 8x8 pixel
+neighborhoods in the fingerprint image that are located within
+a high-curvature region, otherwise cell values are set to 0.
+.TP
+.I <oroot>.lcm
+The \fILow-Contrast Map\fR represents areas in the image having
+low-contrast.  The regions of low contrast most commonly represent
+the background in the fingerprint image.  This is a bi-level map with
+same dimension as the Direction Map.  Cell values of 1
+represent 8x8 pixel neighborhoods in the fingerprint image that are
+located within a low-contrast region, otherwise cell values are set to 0.
+.TP
+.I <oroot>.lfm
+The \fILow-Flow Map\fR represents areas in the image having
+non-determinable ridge flow.  Ridge flow is determined using a set
+of discrete cosine wave forms computed for a predetermined range
+of frequencies.  These wave forms are applied at 16 incremental
+orientations.  At times none of the wave forms at none of the
+orientations resonate sufficiently high within the region in the
+image to satisfactorily determine a dominant directional frequency.
+This is a bi-level map with same dimension as the Direction Map.
+Cell values of 1 represent 8x8 pixel neighborhoods in the fingerprint
+image that are located within a region where a dominant directional
+frequency could \fInot\fR be determined, otherwise cell values are set to 0.
+The Direction Map also records cells with non-determinable ridge
+flow.  The difference is that the Low-Flow Map records \fIall\fR cells
+with non-determinable ridge flow, while the Direction Map records
+only those that remain non-determinable after extensive \fIinterpolation\fR
+and \fIsmoothing\fR of neighboring ridge flow directions.
+.TP
+.I <oroot>.qm
+The \fIQuality Map\fR represents regions in the image having varying
+levels of quality.  The maps above are combined heuristically to form
+5 discrete levels of quality.  This map has the same dimension as the
+Direction Map, with each value in the map representing an 8x8 pixel
+neighborhood in the fingerprint image.  A cell value of 4 represents
+highest quality, while a cell value of 0 represent lowest possible
+quality.
+.TP
+.I <oroot>.xyt
+This text file reports the minutiae detection results.
+This reports only the x,y coordinates, theta, and quality of the
+minutie points for the image.  Each line in this file contains
+the space delimited information for one minutiae point. The
+<oroot>.xyt is the minutiae format used by the \fBbozorth3\fR
+matching algorithm.
+.TP
+.I <oroot>.min
+This text file reports the minutiae detection results.
+The majority of the results listed in this text file are also encoded
+and stored in a Type-9 record in the output ANSI/NIST file.  The
+first non-empty line in the text file lists the number of minutiae
+that were detected in the fingerprint image.  Following this,
+the attributes associated with each detected minutia are recorded,
+one line of text per minutia.  Each minutia line has the same format.
+Fields are separated by a ':', subfields are separated by a ';',
+and items within subfields are separated by a ','.  A minutia line
+may be represented as:
+
+.RE 2
+.RS 2
+\fIMN\fR : \fIMX\fR, \fIMY\fR : \fIDIR\fR : \fIREL\fR : \fITYP\fR : \fIFTYP\fR : \fIFN\fR : \fINX1\fR, \fINY1\fR; \fIRC1\fR : ...
+.PP
+.RE
+.RS
+.RS
+.RS
+where:
+.TP
+.I MN
+is the integer identifier of the detected minutia.
+.TP
+.I MX
+is the x-pixel coordinate of the detected minutia.
+.TP
+.I MY
+is the y-pixel coordinate of the detected minutia.
+.TP
+.I DIR
+is the direction of the detected minutia.  Minutia direction is
+represented similar to ridge flow direction, only minutia direction
+is uni-directional starting at vertical pointing up with unit 0 and
+increasing clockwise in increments of 11.25 degrees completing a
+full circle.  Using this scheme, the angle of a detected minutia is
+quantized into the range 0 to 31 with 8 representing horizontal to the
+right, 16 representing vertical pointing down, and 24 representing
+horizontal to the left.
+.TP
+.I REL
+is the reliability measure assigned to the detected minutia.  This
+measure is computed by looking up the quality level
+associated with the position of the minutia from the Quality Map.
+The quality level is then heuristically combined with simple
+neighborhood pixel statistics surrounding the minutia point.
+The results is a floating point value in the range 0.0 to 1.0,
+with 0.0 representing lowest minutia quality and 1.0 representing
+highest minutia quality.
+.TP
+.I TYP
+is the type of the detected minutia.
+.RS
+bifurcation  = "BIF"
+.br
+ridge ending = "RIG"
+.RE
+.TP
+.I FTYP
+is the type of feature detected.
+.RS
+appearing    = "APP"
+.br
+disappearing = "DIS"
+.br
+(This attribute is primarily useful for
+purposes internal to the minutia detection algorithm.)
+.RE
+.TP
+.I FN
+is the integer identifier of the type of feature detected.
+(This attribute is primarily useful for
+purposes internal to the minutia detection algorithm.)
+.TP
+.I NX1
+is the x-pixel coordinate of the first neighboring minutia.
+.TP
+.I NY1
+is the y-pixel coordinate of the first neighboring minutia.
+.TP
+.I RC1
+is the ridge count calculated between the detected minutia and its
+first neighbor.
+.TP
+.I ...
+for each additional neighbor ridge count computed, the pixel
+coordinate of the neighbor and the ridge count to that neighbor
+are reported.
+
+.SH EXAMPLES
+From \fItest/mindtct/execs/mindtct/mindtct.src\fR:
+.PP
+.RS
+.B % mindtct ../../data/g001t2u.eft g001t2u
+.SH SEE ALSO
+.BR an2k2txt (1F),
+.BR an2ktool (1F),
+.BR dpyan2k (1F),
+.BR bozorth3 (1E)
+
+.SH AUTHOR
+NIST/ITL/DIV894/Image Group

package/libnbis/nbis_x86-64_linux/man/man1/mkoas.1

@@ -0,0 +1,194 @@
+.\" @(#)mkoas.1 2008/10/02 NIST
+.\" I Image Group
+.\" G. T. Candela & Craig I. Watson
+.\"
+.TH MKOAS 1B "02 October 2008" "NIST" "NBIS Reference Manual"
+.SH NAME
+mkoas \- makes orientation arrays from fingerprint images.
+.SH SYNOPSIS
+.B mkoas
+.I <prsfile>
+.SH DESCRIPTION
+.B Mkoas
+makes orientation arrays (oas), for a set of fingerprint image files.
+An oa can be thought of as a 28 (height) by
+30 (width) array of real two-dimensional orientation vectors, each of
+which represents the local average ridge/valley orientation at one
+point of an equally-spaced rectangular grid; but, sometimes it is more
+convenient to think of an oa as a single 1680-dimensional real vector
+(1680 = 28 x 30 x 2).  To make an oa from a fingerprint, mkoas uses
+the same sequence of preprocessing/feature-extraction routines that is
+used by the classifier demos pcasys and pcasysx.  Mkoas causes each
+oa to be one row of the PCASYS "matrix" file that is its output.
+
+Mkoas sets the values of its parameters as follows.  First, it reads
+the default oas-production parms file \fIpcasys/parms/oas.prs\fR; then,
+it reads the file of default values of additional mkoas parms,
+\fIpcasys/parms/mkoas.prs\fR; finally, it reads the required user
+parms file, which is the argument (\fIprsfile\fR).  Each time a parms file
+is read, its values override those set by previously read parms
+file(s), if any.  See PARAMETER FILES, below, for a description of the
+difference between \fIoas.prs\fR and \fImkoas.prs\fR.
+
+Since the oas of a large set of fingerprints can turn out to be
+quite a large amount of data, it may be that the entire set of oas
+that are to be produced cannot exist as a single file, because of
+disk space limitations.  If so, one should run several instances of
+mkoas, each producing a matrix file that is a subset of
+the required oas.  To estimate output file size as a function of
+number of oas, note that each oa consists of 1680
+single-precision floating-point numbers, and therefore it takes 1680
+x 4 = 6720 bytes.  Allow slightly more space, for header data
+contained in a matrix file.
+.SH OPTIONS
+.TP
+.I <prsfile>
+A file containing parameters.  To find out what the available
+parameters are, and as examples of the format of parameters files,
+consult the default files \fIpcasys/parms/oas.prs\fR and
+\fIpcasys/parms/mkoas.prs\fR.  Each parameter is specified
+by having its name and value on a line; a pound sign indicates that
+the rest of its line is a comment.
+.TP
+\fB-version
+\fRPrint ANSI/NIST stardand and NBIS software version.
+
+.SH PARAMETER FILES
+.TP
+.I pcasys/parms/oas.prs
+Contains default values of the parameters that affect the making of
+orientation arrays (oas): these are the parms of the segmentor
+(sgmnt), the image enhancer (enhnc), the ridge-valley orientation
+finder (rors), the registration program (r92a), and the
+registration-implementing pixelwise orientations reaverager (rgar).
+The values used for these parms when making the oas used in
+optimizing the classifier should also be used when running the
+finished classifier.
+.PP
+.RS
+.B Default settings in \fIpcasys/parms/oas.prs\fR
+.TP
+.I Used in the segmentation routine:
+.TP
+.B sgmnt_fac_n \fI5\fR
+How many threshold-making factors to try.
+.TP
+.B sgmnt_min_fg \fI2000\fR
+Minimum allowed number of foreground (true) pixels.
+.TP
+.B sgmnt_max_fg \fI8000\fR
+Maximum allowed number of foreground (true) pixels.
+.TP
+.B sgmnt_nerode \fI3\fR
+Do this many erosions in foreground cleanup.
+.TP
+.B sgmnt_rsblobs \fI1\fR
+If 1, remove small blobs in foreground cleanup.
+.TP
+.B sgmnt_fill \fI1\fR
+If 1, fill holes in rows, columns in foreground cleanup.
+.TP
+.B sgmnt_min_n \fI25\fR
+Cutting angle becomes zero if any foreground edge has fewer than
+this many pixels.
+.TP
+.B sgmnt_hist_thresh \fI20\fR
+Threshold that tilted-rows-histogram must meet to find top-location
+for cutting.
+.TP
+.B sgmnt_origras_wmax \fI2000\fR
+Maximum allowed width of original raster.
+.TP
+.B sgmnt_origras_hmax \fI2000\fR
+Maximum allowed height of original raster.
+.TP
+.B sgmnt_fac_min \fI0.75\fR
+Minimum threshold-making factor value.
+.TP
+.B sgmnt_fac_del \fI0.05\fR
+Delta of threshold-making factor value.
+.TP
+.B sgmnt_slope_thresh \fI0.90\fR
+If any of the three edges has slope differing by more than
+this from the average of the slopes, then cutting angle is set to zero.
+
+.TP
+.I Used in the FFT image enhancer:
+.TP
+.B enhnc_rr1 \fI150\fR
+High-frequency elements of FFT whose filter plane value is less than this
+value are discarded.
+.TP
+.B enhnc_rr2 \fI449\fR
+Low-frequency elements of FFT whose filter plane number is greater than this
+value are discarded.
+.TP
+.B enhnc_pow \fI0.3\fR
+Power spectrum is raised to this power before it is multiplied by
+the FFT output.
+
+.TP
+.I Used in the ridge-valley orientation finder:
+.TP
+.B rors_slit_range_thresh \fI10\fR
+If the difference between the maximum and minimum slit-sums at a pixel
+is less than this, then this pixel makes no contribution to the
+histogram used to make the local average orientation.
+           
+.TP
+.I Used in the r92a wrapper for r92 registration program:
+.TP
+.B r92a_discard_thresh \fI0.01\fR
+If squared-length of a local-average orientation vector is less than this,
+then conversion of this vector to an angle for use by r92 just produces
+the special value 100., which means an undefined angle.
+
+.TP
+.I Used in the registering pixelwise-orientations-reaverager:
+.TP
+.B rgar_std_corepixel_x \fI245\fR
+X coordinate of standard (median) core position.
+.TP
+.B rgar_std_corepixel_y \fI189\fR
+Y coordinate of standard (median) core position.
+This is the standard registration point, to which the particular
+core point gets translated to implement registration.
+.RE
+
+.TP
+.I pcasys/parms/mkoas.prs
+Contains default values of additional parameters needed by  mkoas,
+besides those appearing in \fIpcasys/parms/oas.prs\fR. Parameters without
+defaults values must appear in the users \fIprsfile\fR.
+.PP
+.RS
+.B Default settings in \fIpcasys/parms/mkoas.prs\fR
+.TP
+\fBascii_oas \fIn\fR
+Ascii (y) or binary (n) output?
+.TP
+.B update_freq \fI1\fR
+Frequency of progress messages.
+.TP
+.B clobber_oas_file \fIn\fR
+Overwrite an oas_file if it already exists?
+.TP
+.B proc_images_list \fI(no default, user must set)\fR
+The list of fingerprint images to make orientation arrays from.
+.TP
+.B oas_file \fI(no default, user must set)\fR
+The output file that is to be produced containing orientation arrays.
+.SH EXAMPLE(S)
+From \fItest/pcasys/execs/mkoas/mkoas.src\fR:
+.PP
+.RS
+.B % mkoas sv10.prs
+.br
+Creates a set of orientation arrays based on the file list
+given in the parameters file \fIsv10.prs\fR.
+.SH "SEE ALSO"
+bin2asc (1B), asc2bin (1B), chgdesc (1B), stackms (1B)
+
+
+.SH AUTHOR
+NIST/ITL/DIV894/Image Group

package/libnbis/nbis_x86-64_linux/man/man1/mktran.1

@@ -0,0 +1,72 @@
+.\" @(#)mktran.1 2008/10/02 NIST
+.\" I Image Group
+.\" G. T. Candela & Craig I. Watson
+.\"
+.TH MKTRAN 1B "02 October 2008" "NIST" "NBIS Reference Manual"
+.SH NAME
+mktran \- makes transform matrix from regional weights and
+eigenvectors.
+.SH SYNOPSIS
+.B mktran
+.I <regwts_file> <eigvecs_file> <n_eigvecs_use>
+.I <tranmat_file> <tranmat_file_desc> <ascii_outfile>
+.SH DESCRIPTION
+.B Mktran
+takes a matrix of regional weights, and a set of eigenvectors, and
+makes a transform matrix from the regional weights and the specified
+number of (first) eigenvectors.  The resulting matrix is suitable for
+transforming an orientation array into a low\-dimensional feature
+vector.
+.SH OPTIONS
+.TP
+.I <regwts_file>
+Regional weights file in PCASYS "matrix" format.  The dimensions must
+be 14x15, because that is the pattern of 2x2\-vector blocks of
+orientation vectors. (Usually the output of \fBoptrws\fR.)
+.TP
+.I <eigvecs_file>
+Eigenvectors file in PCASYS "matrix" format.  The first dimension is
+the number of eigenvectors contained in the file; the second dimension
+must be 1680, which is the dimension of an orientation array when it
+is thought of as a single vector. (Usually the output of \fBeva_evt\fR.)
+.TP
+.I <n_eigvecs_use>
+The number (first) eigenvectors to be used.  This will
+be the first dimension of the resulting transform matrix.
+.TP
+.I <tranmat_file>
+Transform file to be made, in PCASYS "matrix" format.  First dimension
+will be \fIn_eigvecs_use\fR and second dimension will be 1680.
+.TP
+.I <tranmat_file_desc>
+A string to be written into the transform matrix output file as its
+description string.  This string can be of any length, but must not
+contain embedded newline characters.  If it contains spaces, tabs, or
+shell metacharacters that are not to be expanded, then it should be
+quoted.  To leave the description empty, use '' (two single quotes,
+i.e.  single\-quoted empty string).  To let mktran make a description,
+use \- (hyphen).
+.TP
+.I <ascii_outfile>
+If y, makes an ascii output file; if n, binary.  Binary is
+recommended, unless the output file must be portable across different
+byte orders or floating\-point formats.
+.TP
+\fB-version
+\fRPrint ANSI/NIST stardand and NBIS software version.
+
+.SH EXAMPLE(S)
+From \fItest/pcasys/execs/mktran/mktran.src\fR:
+.PP
+.RS
+.B % mktran ../optrws/optrws.bin ../eva_evt/fv1-9.evt 64 fv1-9.opt - n
+.br
+Uses a set of optimized regional weights (\fIoptrws.bin\fR) to
+adjust a eigen-vector basis set (\fIfv1-9.evt\fR) and create
+a new transformation matrix (\fIfv1-9.opt\fR) that is used
+to reduce the dimensionality of the feature vectors.
+.SH "SEE ALSO"
+eva_evt (1B), lintran (1B), optrws (1B)
+
+.SH AUTHOR
+NIST/ITL/DIV894/Image Group