updated old ocropus commands

.pynative/73107508b5b80f47b8c46d26c1b5b803.c

@@ -0,0 +1,42 @@
+
+#include <math.h>
+
+void sigmoid(int n,double v[n],double out[n]) {
+    for(int i=0;i<n;i++) {
+        double x = v[i];
+        x = x<-100?-100:x>100?100:x;
+        out[i] = 1.0/(1.0+exp(-x));
+    }
+}
+
+void dotplus(int n,int m,double v[n],double a[n][m],double u[m]) {
+    for(int i=0;i<n;i++) {
+        double total;
+        for(int j=0;j<m;j++) total += a[i][j]*u[j];
+        v[i] += total;
+    }
+}
+
+void prodplus(int n,double u[n],double v[n],double out[n]) {
+    for(int i=0;i<n;i++) {
+        out[i] += u[i]*v[i];
+    }
+}
+
+void sumouter(int r,int n,int m,double a[n][m],double u[r][n],double v[r][m]) {
+    for(int i=0;i<n;i++) {
+        for(int j=0;j<m;j++) {
+            double total = 0.0;
+            for(int k=0;k<r;k++) total += u[k][i]*v[k][j];
+            a[i][j] = total;
+        }
+    }
+}
+
+void sumprod(int r,int n,double u[r][n],double v[r][n],double a[n]) {
+    for(int i=0;i<n;i++) {
+        double total = 0.0;
+        for(int k=0;k<r;k++) total += u[k][i]*v[k][i];
+        a[i] = total;
+    }
+}

lib/treat/workers/formatters/readers/image.rb

@@ -7,8 +7,8 @@
 # statistical natural language modeling, and multi-
 # lingual capabilities."
 #
-# Original paper: Google Ocropus Engine: Breuel, 
-# Thomas M. The Ocropus Open Source OCR System. 
+# Original paper: Google Ocropus Engine: Breuel,
+# Thomas M. The Ocropus Open Source OCR System.
 # DFKI and U. Kaiserslautern, Germany.
 class Treat::Workers::Formatters::Readers::Image
 
@@ -18,26 +18,33 @@ class Treat::Workers::Formatters::Readers::Image
   #
   # - (Boolean) :silent => whether to silence Ocropus.
   def self.read(document, options = {})
-    
+
     read = lambda do |doc|
       self.create_temp_dir do |tmp|
-        `ocropus book2pages #{tmp}/out #{doc.file}`
-        `ocropus pages2lines #{tmp}/out`
-        `ocropus lines2fsts #{tmp}/out`
-        `ocropus buildhtml #{tmp}/out > #{tmp}/output.html`
-        doc.set :file,  "#{tmp}/output.html"
+        # `ocropus book2pages #{tmp}/out #{doc.file}`
+        # `ocropus pages2lines #{tmp}/out`
+        # `ocropus lines2fsts #{tmp}/out`
+        # `ocropus buildhtml #{tmp}/out > #{tmp}/output.html`
+
+        `ocropus-nlbin -o #{tmp}/out #{doc.file}`
+        `ocropus-gpageseg #{tmp}/out/????.bin.png --minscale 2`
+        `ocropus-rpred #{tmp}/out/????/??????.bin.png`
+        `ocropus-hocr #{tmp}/out/????.bin.png -o #{tmp}/book.html`
+        doc.set :file,  "#{tmp}/book.html"
         doc.set :format, :html
+
         doc = doc.read(:html)
       end
     end
-    
-    Treat.core.verbosity.silence ? silence_stdout { 
+
+
+    Treat.core.verbosity.silence ? silence_stdout {
     read.call(document) } : read.call(document)
-    
+
     document
-    
+
   end
-  
+
   # Create a dire that gets deleted after execution of the block.
   def self.create_temp_dir(&block)
     if not FileTest.directory?(Treat.paths.tmp)
@@ -50,5 +57,5 @@ class Treat::Workers::Formatters::Readers::Image
   ensure
     FileUtils.rm_rf(dname)
   end
-  
+
 end