diff --git a/src/para_facematch.py b/src/para_facematch.py
index 297094f75..f610a250f 100644
--- a/src/para_facematch.py
+++ b/src/para_facematch.py
@@ -15,6 +15,8 @@ import paravision.recognition.utils as pru
  
 class Facematch(object):
 
+    errstr = ""
+
     def init(self):
         print("@@@ initialising paravision")
         try:
@@ -62,27 +64,36 @@ class Facematch(object):
         print("## loading images", dev1, dev2)
         self.dev1 = dev1
         self.dev2 = dev2
+        errstr = ""
         try:
             # Load images
+            errstr = "id image load"  
             self.id_image = pru.load_image(id_image_filepath)
+            errstr = "client photo load"
             self.photo_image = pru.load_image(photo_image_filepath)
-            print("++++++++++++++++ ",self.id_image)
+            #print("++++++++++++++++ ",self.id_image)
             return True
         except Exception as e:
             print("uk oh loading failed ", e)
-            return None
+            return False
 
 
     def get_faces(self):
+        print("# get faces...")
+        errstr = ""
         try:
             # Get all faces from images with qualities, landmarks, and embeddings
+            errstr = "getting faces"
             self.inference_result = self.sdk.get_faces([self.id_image, self.photo_image], qualities=True, landmarks=True, embeddings=True)
             self.image_inference_result = self.inference_result.image_inferences
             if len(self.image_inference_result)==0:
                 return "no inferences found"
 
             # Get most prominent face
+            print("most prominent...")
+            errstr = "getting most prominent id face"
             self.id_face = self.image_inference_result[0].most_prominent_face_index()
+            errstr = "getting most prominent id face"
             self.photo_face = self.image_inference_result[1].most_prominent_face_index()
             if self.id_face<0:
                 return "no id face found"
@@ -90,23 +101,27 @@ class Facematch(object):
                 return "no live face found"
 
             # Get numerical representation of faces (required for face match)
+            print("digesting...")
+            errstr = "getting numericals"
             if (len(self.image_inference_result)<2):
                 return "ID or human face could not be recognised"
             self.id_emb = self.image_inference_result[0].faces[self.id_face].embedding
             self.photo_emb = self.image_inference_result[1].faces[self.photo_face].embedding
 
         except Exception as ex:
-            return "image processing exception "+str(ex)
-
-        return None
+            errstr = "image processing exception "+str(ex)
+            return False
+        return True
 
 
 #       return " id=%d photo=%d result=%d " % (self.id_face, self.photo_face, len(self.image_inference_result))
 
 
     def compute_scores(self):
+        print("## compute scores...")
         try:
             # Get image quality scores (how 'good' a face is)
+            errstr = "getting image quality"
             self.id_qual = self.image_inference_result[0].faces[self.id_face].quality
             self.photo_qual = self.image_inference_result[1].faces[self.photo_face].quality
 
@@ -114,6 +129,7 @@ class Facematch(object):
             self.photo_qual = round(self.photo_qual, 3)
 
             # Get face match score
+            errstr = "scoring"
             self.match_score = self.sdk.get_match_score(self.id_emb, self.photo_emb)
 
             # Create .json
@@ -137,7 +153,11 @@ class Facematch(object):
                 #print(response.read())
 
         except Exception as ex:
-            return str(ex)
+            errstr = str(ex)
+            return False
+
+        return True
+
 
 
     def get_scores(self):
diff --git a/src/yoloserv.py b/src/yoloserv.py
index 6350c0bfc..56805109a 100644
--- a/src/yoloserv.py
+++ b/src/yoloserv.py
@@ -179,14 +179,17 @@ class yoloserv(object):
         if self.conf["emulate_facematch"]:
             return '{ "status":0, "remark":"OK", "data":{} }' 
 
-        self.facematcher.load(dev1, dev2, img1, img2)
+        status = self.facematcher.load(dev1, dev2, img1, img2)
+        if not status:
+            return '{ "status":777242, "remark":"face loading failed", "guilty_param":"facematch", "guilty_value":"%s" }' % (self.facematcher.errstr)
+
         status = self.facematcher.get_faces()
-        if status is not None:
-            return '{ "status":777242, "remark":"face matching failed", "guilty_param":"facematch", "guilty_value":"%s" }' % (status)
+        if not status:
+            return '{ "status":777245, "remark":"face finding failed", "guilty_param":"facematch", "guilty_value":"%s" }' % (self.facematcher.errstr)
 
         status = self.facematcher.compute_scores()
-        if status is not None:
-            return '{ "status":777243, "remark":"face scoring failed", "guilty_param":"facematch", "guilty_value":"%s" }' % (status)
+        if not status:
+            return '{ "status":777243, "remark":"face scoring failed", "guilty_param":"facematch", "guilty_value":"%s" }' % (self.facematch.errstr)
 
         jsonstr = self.facematcher.get_scores()
         return '{ "status":0, "remark":"OK", "data":%s }' % (jsonstr)