From 5cb160432a1f8f09440fea8162f27013b3aa6af8 Mon Sep 17 00:00:00 2001
From: Admin <admin@viaeon.com>
Date: Fri, 17 Jul 2026 13:14:41 +0000
Subject: [PATCH] fix: scale YOLO coordinates from 640x640 to original image
 size, add debug output

---
 internal/captcha/handler.go | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/internal/captcha/handler.go b/internal/captcha/handler.go
index 6e45917..f679e3a 100644
--- a/internal/captcha/handler.go
+++ b/internal/captcha/handler.go
@@ -869,6 +869,10 @@ func (h *Handler) detectYOLO(modelName, imageBase64 string) (*DetectionResult, e
 		return nil, err
 	}
 
+	// 获取原图尺寸
+	origW := img.Bounds().Dx()
+	origH := img.Bounds().Dy()
+
 	// 预处理：Resize 到 640x640，归一化
 	input, err := preprocessYOLO(img)
 	if err != nil {
@@ -882,8 +886,8 @@ func (h *Handler) detectYOLO(modelName, imageBase64 string) (*DetectionResult, e
 	}
 
 	// YOLO11 输出: [1, 5, 8400] 或 [1, 84, 8400]
-	// 需要转置 + NMS 后处理
-	detections := postprocessYOLO(output, 640, 640, 0.25, 0.45)
+	// 需要转置 + NMS 后处理，坐标从 640x640 缩放到原图尺寸
+	detections := postprocessYOLO(output, origW, origH, 0.25, 0.45)
 
 	result := &DetectionResult{
 		Detections: make([]Detection, len(detections)),
@@ -896,6 +900,8 @@ func (h *Handler) detectYOLO(modelName, imageBase64 string) (*DetectionResult, e
 		}
 	}
 
+	fmt.Printf("DEBUG YOLO '%s': detected %d objects, origSize=%dx%d\n", modelName, len(detections), origW, origH)
+
 	return result, nil
 }
 
@@ -928,7 +934,7 @@ func preprocessYOLO(img image.Image) ([]float32, error) {
 }
 
 // postprocessYOLO YOLO11 后处理
-func postprocessYOLO(output []float32, imgW, imgH int, confThresh, nmsThresh float64) []YOLODetection {
+func postprocessYOLO(output []float32, origW, origH int, confThresh, nmsThresh float64) []YOLODetection {
 	// YOLO11 输出格式: [1, 5, 8400] 或 [1, 84, 8400]
 	// 5 = x, y, w, h, conf (单类)
 	// 84 = x, y, w, h, conf*80 (80类)
@@ -955,6 +961,10 @@ func postprocessYOLO(output []float32, imgW, imgH int, confThresh, nmsThresh flo
 	// 类别名称（根据模型调整）
 	classNames := []string{"icon"} // Detection_Icon 只有一个类
 
+	// 坐标缩放比例：从 640x640 到原图
+	scaleX := float64(origW) / 640.0
+	scaleY := float64(origH) / 640.0
+
 	detections := []YOLODetection{}
 
 	// 遍历所有检测框
@@ -988,6 +998,12 @@ func postprocessYOLO(output []float32, imgW, imgH int, confThresh, nmsThresh flo
 		w := float64(output[wIdx])
 		h := float64(output[hIdx])
 
+		// 缩放坐标到原图尺寸
+		cx *= scaleX
+		cy *= scaleY
+		w *= scaleX
+		h *= scaleY
+
 		// 转换为 x1, y1, x2, y2
 		x1 := cx - w/2
 		y1 := cy - h/2