Update server1.py

server1.py

@@ -2,91 +2,54 @@
 
 import io
 import numpy as np
+import cv2
 from fastapi import FastAPI, UploadFile, File
 from fastapi.responses import JSONResponse
 from PIL import Image
-import torch
-
-from transformers import SamModel, SamProcessor
 
 app = FastAPI(title="Accudoctor Strip Analyzer")
 
-DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
-
-# modelo abierto que SI funciona
-model = SamModel.from_pretrained("facebook/sam-vit-base").to(DEVICE)
-processor = SamProcessor.from_pretrained("facebook/sam-vit-base")
-
-def dominant_color(pil_img):
-    img = pil_img.resize((60, 60))
-    arr = np.array(img).reshape((-1, 3))
-
-    pixels, counts = np.unique(arr, axis=0, return_counts=True)
-    dom = pixels[counts.argmax()]
-
-    return "#{:02x}{:02x}{:02x}".format(dom[0], dom[1], dom[2])
-
-def analyze_strip(image_bytes):
-
-    img = Image.open(io.BytesIO(image_bytes))
-    if img.mode != "RGB":
-        img = img.convert("RGB")
+def contar_cuadrados(image_bytes):
 
-    inputs = processor(img, return_tensors="pt").to(DEVICE)
-
-    with torch.no_grad():
-        outputs = model(**inputs)
-
-    masks = processor.post_process_masks(
-        outputs.pred_masks.cpu(),
-        inputs["original_sizes"].cpu(),
-        inputs["reshaped_input_sizes"].cpu()
-    )[0].numpy()
-
-    blocks = []
+    img = Image.open(io.BytesIO(image_bytes)).convert("RGB")
     np_img = np.array(img)
-    H, W = np_img.shape[:2]
 
-    for mask in masks:
-        ys, xs = np.where(mask > 0.5)
-        if len(xs) == 0:
-            continue
+    gray = cv2.cvtColor(np_img, cv2.COLOR_RGB2GRAY)
+    blur = cv2.GaussianBlur(gray, (5,5), 0)
 
-        x1, x2 = xs.min(), xs.max()
-        y1, y2 = ys.min(), ys.max()
+    # bordes
+    edges = cv2.Canny(blur, 50, 150)
 
-        w = x2 - x1
-        h = y2 - y1
+    # contornos
+    contours, _ = cv2.findContours(edges, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
 
-        if h / (w + 1e-6) < 3:
-            continue
+    cuadrados = []
 
-        if h < H * 0.04:
-            continue
+    for cnt in contours:
+        approx = cv2.approxPolyDP(cnt, 0.04 * cv2.arcLength(cnt, True), True)
 
-        crop = img.crop((x1, y1, x2, y2))
-        color = dominant_color(crop)
+        # queremos formas cuadradas / rectangulares
+        if len(approx) == 4 and cv2.contourArea(cnt) > 200:
+            x, y, w, h = cv2.boundingRect(cnt)
 
-        blocks.append({
-            "bbox": [int(x1), int(y1), int(x2), int(y2)],
-            "color_hex": color,
-            "y_center": (y1 + y2) / 2
-        })
-
-    blocks = sorted(blocks, key=lambda b: b["y_center"])
+            if w > 10 and h > 10:
+                cuadrados.append({
+                    "bbox": [int(x), int(y), int(x+w), int(y+h)]
+                })
 
-    for i, b in enumerate(blocks):
-        b["index"] = i + 1
-        del b["y_center"]
+    return cuadrados
 
-    return blocks[:11]
 
 @app.post("/strip/")
 async def strip(front: UploadFile = File(...)):
     try:
         bytes_img = await front.read()
-        result = analyze_strip(bytes_img)
+        cuadrados = contar_cuadrados(bytes_img)
 
-        return JSONResponse(content={"code": 200, "blocks": result})
+        return JSONResponse(content={
+            "code": 200,
+            "count": len(cuadrados),
+            "cuadrados": cuadrados
+        })
     except Exception as e:
         return JSONResponse(content={"code": 500, "error": str(e)})